AI Generates New Classical Music - Machine Learning using LSTM

Codes in The Description

Predictive Coding Approximates Backprop along Arbitrary Computation Graphs (Paper Explained)

#ai #biology #neuroscience Backpropagation is the workhorse of modern deep learning and a core component of most frameworks, but it has long been known that it is not biologically plausible, driving a divide between neuroscience and machine learning. This paper shows that Predictive Coding, a much more biologically plausible algorithm, can approximate Backpropagation for any computation graph, which they verify experimentally by building and training CNNs and LSTMs using Predictive Coding. This suggests that the brain and deep neural networks could be much more similar than previously believed. OUTLINE: 0:00 - Intro & Overview 3:00 - Backpropagation & Biology 7:40 - Experimental Results 8:40 - Predictive Coding 29:00 - Pseudocode 32:10 - Predictive Coding approximates Backprop 35:00 - Hebbian Updates 36:35 - Code Walkthrough 46:30 - Conclusion & Comments Paper: https://ift.tt/3mndCnZ Code: https://ift.tt/35bLGvP Abstract: Backpropagation of error (backprop) is a powerful algorithm for training machine learning architectures through end-to-end differentiation. However, backprop is often criticised for lacking biological plausibility. Recently, it has been shown that backprop in multilayer-perceptrons (MLPs) can be approximated using predictive coding, a biologically-plausible process theory of cortical computation which relies only on local and Hebbian updates. The power of backprop, however, lies not in its instantiation in MLPs, but rather in the concept of automatic differentiation which allows for the optimisation of any differentiable program expressed as a computation graph. Here, we demonstrate that predictive coding converges asymptotically (and in practice rapidly) to exact backprop gradients on arbitrary computation graphs using only local learning rules. We apply this result to develop a straightforward strategy to translate core machine learning architectures into their predictive coding equivalents. We construct predictive coding CNNs, RNNs, and the more complex LSTMs, which include a non-layer-like branching internal graph structure and multiplicative interactions. Our models perform equivalently to backprop on challenging machine learning benchmarks, while utilising only local and (mostly) Hebbian plasticity. Our method raises the potential that standard machine learning algorithms could in principle be directly implemented in neural circuitry, and may also contribute to the development of completely distributed neuromorphic architectures. Authors: Beren Millidge, Alexander Tschantz, Christopher L. Buckley Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB Parler: https://ift.tt/38tQU7C LinkedIn: https://ift.tt/2Zo6XRA If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Webinar Indonesia ID5G Ecosystem x BISA AI #38 – Tutorial Orange Untuk Data Science dan Machine Lear

Webinar Indonesia ID5G Ecosystem x BISA AI #38 – Tutorial Orange Untuk Data Science dan Machine Learning Orange adalah software analisis dan visualisasi data tanpa kode. Untuk pemula, software ini cocok digunakan sebagai pengenalan dan eksplorasi dasar-dasar Data Science dan Machine Learning. Namun ada juga fitur-fitur yang dapat digunakan untuk membantu modelling dan projek tingkat lanjut lainnya. Ikuti webinar ID5G x BISA AI #38 untuk sama-sama belajar Data Science dan Machine Learning tanpa menggunakan kodingan! Bersama : - M. Octaviano Pratama, S.Kom., M.Kom Co Founder BISA AI Acara ini akan dilaksanakan pada : Kamis, 03 Desember 2020 19.00 WIB – Selesai Langsung dari BISA Tampil dan YouTube BISA AI --- 📌 Playlist video event workshop, seminar, dan talkshow dari berbagai narasumber mengenai Python, AI, dll di: https://www.youtube.com/playlist?list=PLwEzEX1KA1ngauZlV1lQLk7XSBtifdSgL --- 📌 Lihat event-event selanjutnya di: https://bisa.ai/tampil/event --- Visit our website at : https://bisa.ai Blog at : https://medium.com/bisa-ai Instagram : https://www.instagram.com/bisa.ai/ Contact Person (BISA.AI) : +62-8211-6654-087 for latest info and events

Tutorial on Artificial Intelligence: Deep Learning: Methodology Season #2/1.

Check out the Season 2 of our 12-episode web series dedicated to AI This 1st episode features Alexandre Valentian who walks us through the requirements for DeepLearning methodology, including the need to clearly define the problem and prepare & collect data ....So we hope this teaser makes you want to view and enjoy the first cap of Season#2 on Artificial Intelligence ! For more information ⏩Visit CEA-List Website: http://www-list.cea.fr/en/ ⏩Follow them on LinkedIn: linkedin.com/company/cealist ⏩Visit MIAI website: https://miai.univ-grenoble-alpes.fr/ ⏩Follow them on LinkedIn: linkedin.com/company/miai-grenoble-alpes/ ⏩ Visit our Website: https://www.leti-cea.com/cea-tech/leti... ⏩ Follow us on LinkedIn: linkedin.com/company/leti ⏩ Don't miss our corporate video : http://bit.ly/CEALeti 🔔 Subscribe to our channel: http://bit.ly/suscribe-CEALeti Thank you for watching !

Remember, This Meeting Never Happened! 🚶🚶‍♀️

❤️ Check out Weights & Biases and sign up for a free demo here: https://ift.tt/2YuG7Yf ❤️ Their report on this exact paper is available here: https://ift.tt/37iZZjd 📝 The paper "Layered Neural Rendering for Retiming People in Video" is available here: https://ift.tt/3cGOmoP 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Serban, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Jace O'Brien, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Webinar Indonesia ID5G Ecosystem x BISA AI #38 – Tutorial Orange Untuk Data Science dan Machine Lear

Webinar Indonesia ID5G Ecosystem x BISA AI #38 – Tutorial Orange Untuk Data Science dan Machine Learning Orange adalah software analisis dan visualisasi data tanpa kode. Untuk pemula, software ini cocok digunakan sebagai pengenalan dan eksplorasi dasar-dasar Data Science dan Machine Learning. Namun ada juga fitur-fitur yang dapat digunakan untuk membantu modelling dan projek tingkat lanjut lainnya. Ikuti webinar ID5G x BISA AI #38 untuk sama-sama belajar Data Science dan Machine Learning tanpa menggunakan kodingan! Bersama : - M. Octaviano Pratama, S.Kom., M.Kom Co Founder BISA AI Acara ini akan dilaksanakan pada : Kamis, 03 Desember 2020 19.00 WIB – Selesai Langsung dari BISA Tampil dan YouTube BISA AI --- 📌 Playlist video event workshop, seminar, dan talkshow dari berbagai narasumber mengenai Python, AI, dll di: https://www.youtube.com/playlist?list=PLwEzEX1KA1ngauZlV1lQLk7XSBtifdSgL --- 📌 Lihat event-event selanjutnya di: https://bisa.ai/tampil/event --- Visit our website at : https://bisa.ai Blog at : https://medium.com/bisa-ai Instagram : https://www.instagram.com/bisa.ai/ Contact Person (BISA.AI) : +62-8211-6654-087 for latest info and events

Tutorial on Artificial Intelligence: Deep Learning: Methodology Season #2/1.

Check out the Season 2 of our 12-episode web series dedicated to AI This 1st episode features Alexandre Valentian who walks us through the requirements for DeepLearning methodology, including the need to clearly define the problem and prepare & collect data ....So we hope this teaser makes you want to view and enjoy the first cap of Season#2 on Artificial Intelligence ! For more information ⏩Visit CEA-List Website: http://www-list.cea.fr/en/ ⏩Follow them on LinkedIn: linkedin.com/company/cealist ⏩Visit MIAI website: https://miai.univ-grenoble-alpes.fr/ ⏩Follow them on LinkedIn: linkedin.com/company/miai-grenoble-alpes/ ⏩ Visit our Website: https://www.leti-cea.com/cea-tech/leti... ⏩ Follow us on LinkedIn: linkedin.com/company/leti ⏩ Don't miss our corporate video : http://bit.ly/CEALeti 🔔 Subscribe to our channel: http://bit.ly/suscribe-CEALeti Thank you for watching !

Univ.AI | Demo class 2 | The Essence of Machine Learning by Dr. Rahul Dave

Training and deploying ML models on edge devices (TF Fall 2020 Updates)

Learn how to train and deploy an ML model on an Android app in just a few lines of code with TensorFlow Lite Model Maker and Android Studio. From here you can then explore how to use various tools from Google to turn a prototype into a production app. Presented by Khanh LeViet, Developer Advocate for TensorFlow (@khanlvg). Flower classification codelab → https://goo.gle/3pJeh56 TF Lite pretrained models → https://goo.gle/2Uvr3a9 Learn more about TF Lite → https://goo.gle/2Wk5MPM Check out more TF Fall 2020 updates → https://goo.gle/tf-fall-updates Subscribe to TensorFlow → https://goo.gle/TensorFlow #tensorflowupdates

AI-Based Sky Replacement Is Here! 🌓

❤️ Check out Weights & Biases and sign up for a free demo here: https://ift.tt/2YuG7Yf ❤️ Their report on this paper is available here: https://ift.tt/2IVQf6H 📝 The paper "Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos" is available here: https://ift.tt/2TpVflx ☀️The mentioned free light transport course is available here: https://ift.tt/2rdtvDu 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Jace O'Brien, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Univ.AI | Demo class 2 | The Essence of Machine Learning by Dr. Rahul Dave

Intro to On-device Machine Learning (TF Fall 2020 Updates)

In this session, Developer Advocate Khanh LeViet (@khanhlvg) talks about TensorFlow Lite, the framework that brings ML to mobile and embedded systems. You'll learn about the differences between ML on a supercomputer and ML on a portable device, and the tools and technologies that Google has developed to allow you to bring your work to mobile devices without reinventing the wheel. We'll cover the basics and also special subjects like TinyML and model optimization and quantization. Learn more about TensorFlow Lite → https://goo.gle/2Wk5MPM TensorFlow Lite example apps → https://goo.gle/3byxWNf TensorFlow Lite for Microcontrollers → https://goo.gle/2yiYyUl Robotic vacuum cleaner powered by TF → https://goo.gle/36MmhtI Check out more TF Fall 2020 updates → https://goo.gle/tf-fall-updates Subscribe to TensorFlow → https://goo.gle/TensorFlow

Fourier Neural Operator for Parametric Partial Differential Equations (Paper Explained)

#ai #research #engineering Numerical solvers for Partial Differential Equations are notoriously slow. They need to evolve their state by tiny steps in order to stay accurate, and they need to repeat this for each new problem. Neural Fourier Operators, the architecture proposed in this paper, can evolve a PDE in time by a single forward pass, and do so for an entire family of PDEs, as long as the training set covers them well. By performing crucial operations only in Fourier Space, this new architecture is also independent of the discretization or sampling of the underlying signal and has the potential to speed up many scientific applications. OUTLINE: 0:00 - Intro & Overview 6:15 - Navier Stokes Problem Statement 11:00 - Formal Problem Definition 15:00 - Neural Operator 31:30 - Fourier Neural Operator 48:15 - Experimental Examples 50:35 - Code Walkthrough 1:01:00 - Summary & Conclusion Paper: https://ift.tt/2UQQguM Blog: https://ift.tt/3kUGMZW Code: https://ift.tt/3nMENJf MIT Technology Review: https://ift.tt/31XXdy7 Abstract: The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution. Thus, they learn an entire family of PDEs, in contrast to classical methods which solve one instance of the equation. In this work, we formulate a new neural operator by parameterizing the integral kernel directly in Fourier space, allowing for an expressive and efficient architecture. We perform experiments on Burgers' equation, Darcy flow, and the Navier-Stokes equation (including the turbulent regime). Our Fourier neural operator shows state-of-the-art performance compared to existing neural network methodologies and it is up to three orders of magnitude faster compared to traditional PDE solvers. Authors: Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB Parler: https://ift.tt/38tQU7C LinkedIn: https://ift.tt/2Zo6XRA If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Near-Perfect Virtual Hands For Virtual Reality! 👐

❤️ Check out Lambda here and sign up for their GPU Cloud: https://ift.tt/35NkCT7 📝 The paper "MEgATrack: Monochrome Egocentric Articulated Hand-Tracking for Virtual Reality" is available here: https://ift.tt/3lRFHn3 ❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: - https://ift.tt/2icTBUb - https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Thumbnail background image credit: https://ift.tt/335bVUI Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Zero to Hero with TensorFlow (TF Fall 2020 Updates)

If you're interested in ML, but didn't know where to start, this talk will help you understand the paradigm of ML and how TensorFlow can be used to train machine-learned models. AI Advocate Laurence Moroney (@lmoroney) will show you how to use some of the latest and greatest features in TensorFlow that let you go from nothing to a working ML model in just a few minutes. No PhD required. The “Hello, World” of ML codelab → https://goo.gle/2Zp2ZF3 Check out more TF Fall 2020 updates → https://goo.gle/tf-fall-updates Subscribe to TensorFlow → https://goo.gle/TensorFlow

No Code Machine Learning Microsoft Tool Lobe.AI Tutorial | Deep Learning

Microsoft recently launched its No Code Machine Learning / Deep Learning Tool Lobe.ai. In this tutorial, you'll learn how to build a simple Deep Learning (Computer Vision) Model to detect Dogs vs Cats. This tool is a desktop based tool that can also let you export your model into CoreML, Tensorflow, Tensorflow Lite or just expose it as a Simple API. This tool is almost similar to Google's Teachable - https://www.youtube.com/watch?v=dwHv1ol9J14 https://lobe.ai/ Lobe iOS / Web App / Python Templates - https://github.com/lobe/

Python Chat Bot Tutorial - AI Chatbot with Deep Learning (BONUS)

This is just a quick bonus video for any of you interested in some of the applications of the chat bot. I show you how I've used it in my discord server and how to add whats known as a confidence for our bots responses. This way when the bot can give an reasonable answer if its not sure what the user is saying. Playlist: https://www.youtube.com/watch?v=wypVcNIH6D4&list=PLzMcBGfZo4-ndH9FoC4YWHGXG5RZekt-Q ◾◾◾◾◾ 💻 Enroll in The Fundamentals of Programming w/ Python https://tech-with-tim.teachable.com/p... 📸 Instagram: https://www.instagram.com/tech_with_tim 🌎 Website https://techwithtim.net 📱 Twitter: https://twitter.com/TechWithTimm ⭐ Discord: https://discord.gg/pr2k55t 📝 LinkedIn: https://www.linkedin.com/in/tim-rusci... 📂 GitHub: https://github.com/techwithtim 🔊 Podcast: https://anchor.fm/tech-with-tim 💵 One-Time Donations: https://www.paypal.com/donate/?token=... 💰 Patreon: https://www.patreon.com/techwithtim ◾◾◾◾◾◾ ⚡ Please leave a LIKE and SUBSCRIBE for more content! ⚡ Tags: - Tech With Tim - Python Tutorials - Python AI Chatot - AI chat bot tutorial

Nvidia AI Deep Learning Painting GauGAN Online Interactive Demo

Saw a lot of friends are playing with Nvidia AI deep learning painting app online. Decide to try it too. There are option to upload your landscape image and style guide image too. You can try the demo in the following link https://www.nvidia.com/en-us/research/

Introduction to AI and Machine Learning

Event page: https://developer.ibm.com/videos/tech-talk-an-introduction-to-ai-and-machine-learning/ Machine learning is branching out across numerous fields, one of the most interesting fields is health care. In this tech talk, we will go through an overview of what Machine Learning and Artificial Intelligence are, explaining at a high level key concepts such as models and classifiers. Afterwards, we will go through an example of how to train a machine learning model to predict type 2 diabetes using synthesized patient health records. This talk will demo preparing data using Apache Spark, visualizing data relationships using PixieDust, training a model, and deploying it to receive predictions. Resources Mentioned: 1) https://github.com/IBM/predictive-model-on-watson-ml 2) https://github.com/IBM/summit-health-machine-learning

Mini-Tutorial/Workshop: Machine Learning/AI

Aaron Saxton from NCSA presents the mini tutorial/workshop "Machine Learning/AI"

TWiML x Fast.ai Deep Learning Part 2 Study Group - Prep

This is a recording of the June 22nd TWiML revision study group session for the review of Practical Deep Learning for Coders (aka Part 1) course in preparation for Part 2. This session covers Lesson 1 & 2 of the course: Image Classification and Data cleaning and production; SGD from scratch. It’s not too late to join the study group. Just follow these simple steps: 1. Head over to twimlai.com/meetup, and sign up for the programs you're interested in, including either of the Fast.ai study groups or our Monthly Meetup groups. 2. Use the email invitation you’ll receive to join our Slack group. If you don’t receive it within a few minutes, check your spam folder. 3. Once you’re in Slack, join the #fast_ai channel and hop over to #intros as well and introduce yourself. 4. Use the link posted in the #meetup slack channel to add our events to your calendar. Subscribe! iTunes ➙ https://itunes.apple.com/us/podcast/twimlai Soundcloud ➙ https://soundcloud.com/twiml Google Play ➙ http://bit.ly/2lrWlJZ Stitcher ➙ http://www.stitcher.com/s?fid=92079&r RSS ➙ https://twimlai.com/feed Subscribe to our newsletter! ➙ https://twimlai.com/newsletter Lets Connect! Twimlai.com ➙ https://twimlai.com/contact Twitter ➙ https://twitter.com/twimlai Facebook ➙ https://Facebook.com/Twimlai Medium ➙ https://medium.com/this-week-in-machine-learning **SUBSCRIBE AND TURN ON NOTIFICATIONS**

TensorFlow Fall 2020 updates - Keynote & what’s new since TF2.2

To support TensorFlow's continuing growth and scale, we are excited to share the latest in TF2.x for Fall 2020. Join AI Advocate Laurence Moroney (@lmoroney) for product updates across the ecosystem from research, to production, to deployment, new resources to support Responsible AI, and community updates and tips on how to get more involved! From Keynote: TensorFlow supports Google Meet → https://goo.gle/3ntPLD6 Responsible AI with TensorFlow Toolkit → https://goo.gle/3kFZ94X Certificate in TensorFlow Development → https://goo.gle/3b6IKlz HarvardX TinyML course → https://goo.gle/3pCTVur TensorFlow Trusted Partner Program → https://goo.gle/2OHJLao Developer Advocate Josh Gordon (@random_forests) also presents a technical round up of what's new in TF in 2020, including TF Agents for reinforcement learning, tf.experimental.numpy, and tools for exploring your model's performance. Join us for a rapid-fire look at many new features. From technical roundup: TensorFlow tutorials → https://goo.gle/3kApD7S Keras preprocessing layers guide → https://goo.gle/2HbByLH NumPy API on TensorFlow guide → https://goo.gle/2TMDi0Q TensorFlow Recommenders → https://goo.gle/2IJAkrK tf.data.Dataset.prefetch → https://goo.gle/2UyOaj4 tf.data.Dataset.cache → https://goo.gle/3fgWbTu Optimize pipeline performance → https://goo.gle/38wyKAy Using the TF Profiler → https://goo.gle/3kIcvgS tf.data.snapshot → https://goo.gle/3lH2O3O tf.data.service → https://goo.gle/3f7JMks tf.data service on GKE example → https://goo.gle/3lGng4X Bonus: Neural Radiance Fields → https://goo.gle/38TRIEP Subscribe to TensorFlow → https://goo.gle/TensorFlow

Is Videoconferencing With Smart Glasses Possible? 👓

❤️ Check out Weights & Biases and sign up for a free demo here: https://ift.tt/2YuG7Yf ❤️ Their mentioned post is available here: https://ift.tt/2IBBeqw 📝 The paper "Egocentric Videoconferencing" is available here: https://ift.tt/3pyAVNP 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Thumbnail background image credit: https://ift.tt/32Ty2NC Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

[News] Soccer AI FAILS and mixes up ball and referee's bald head.

This soccer camera is operated by an AI to track the ball. However, the AI has an interesting failure mode and repeatedly mixes up the ball with the bald head of a referee. This raises some interesting questions about the role of ethics in AI research. Footage from SPFL Championship : ICTFC 1 v 1 AYR : 24/10/2020 Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB Parler: https://ift.tt/38tQU7C LinkedIn: https://ift.tt/2Zo6XRA If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

This AI Makes Puzzle Solving Look Easy! 🧩

❤️ Check out Weights & Biases and sign up for a free demo here: https://ift.tt/2YuG7Yf ❤️ Their mentioned post is available here: https://ift.tt/2SIjBr4 📝 The paper "C-Space Tunnel Discovery for Puzzle Path Planning" is available here: https://ift.tt/3npT2DK https://ift.tt/3nvns7D 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Attomoto by James Seo - Made with TensorFlow.js

In our 8th episode of Made with TensorFlow.js we head to the USA to meet with James Seo who has created a visually stunning mixed reality demo to help us understand human pose over space and time that can be inspected from any angle you desire using WebXR. Attomoto by James Seo → https://goo.gle/2FGgJaj Watch more of Made with TensorFlow.js → http://goo.gle/made-with-tfjs Subscribe to TensorFlow to stay up to date → https://goo.gle/TensorFlow #TensorFlow #TensorFlowJS #MadeWithTFJS #JavaScript #CreativeCoding #WebDev #PoseNet #BodyTracking #MixedReality #WebXR, #AugmentedReality, #AR #Time #Muybridge #Animation #motion #visualization #mobile #webApp #futureTech, #p5XR

Underspecification Presents Challenges for Credibility in Modern Machine Learning (Paper Explained)

#ai #research #machinelearning Deep Learning models are often overparameterized and have many degrees of freedom, which leads to many local minima that all perform equally well on the test set. But it turns out that even though they all generalize in-distribution, the performance of these models can be drastically different when tested out-of-distribution. Notably, in many cases, a good model can actually be found among all these candidates, but it seems impossible to select it. This paper describes this problem, which it calls underspecification, and gives several theoretical and practical examples. OUTLINE: 0:00 - Into & Overview 2:00 - Underspecification of ML Pipelines 11:15 - Stress Tests 12:40 - Epidemiological Example 20:45 - Theoretical Model 26:55 - Example from Medical Genomics 34:00 - ImageNet-C Example 36:50 - BERT Models 56:55 - Conclusion & Comments Paper: https://ift.tt/36gC4kd Abstract: ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline is underspecified when it can return many predictors with equivalently strong held-out performance in the training domain. Underspecification is common in modern ML pipelines, such as those based on deep learning. Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains. This ambiguity can lead to instability and poor model behavior in practice, and is a distinct failure mode from previously identified issues arising from structural mismatch between training and deployment domains. We show that this problem appears in a wide variety of practical ML pipelines, using examples from computer vision, medical imaging, natural language processing, clinical risk prediction based on electronic health records, and medical genomics. Our results show the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain. Authors: Alexander D'Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D. Hoffman, Farhad Hormozdiari, Neil Houlsby, Shaobo Hou, Ghassen Jerfel, Alan Karthikesalingam, Mario Lucic, Yian Ma, Cory McLean, Diana Mincu, Akinori Mitani, Andrea Montanari, Zachary Nado, Vivek Natarajan, Christopher Nielson, Thomas F. Osborne, Rajiv Raman, Kim Ramasamy, Rory Sayres, Jessica Schrouff, Martin Seneviratne, Shannon Sequeira, Harini Suresh, Victor Veitch, Max Vladymyrov, Xuezhi Wang, Kellie Webster, Steve Yadlowsky, Taedong Yun, Xiaohua Zhai, D. Sculley Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB Parler: https://ift.tt/38tQU7C LinkedIn: https://ift.tt/2Zo6XRA If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Making Talking Memes With Voice DeepFakes!

❤️ Check out Lambda here and sign up for their GPU Cloud: https://ift.tt/35NkCT7 📝 The paper "Wav2Lip: Accurately Lip-syncing Videos In The Wild" is available here: - Paper: https://ift.tt/2ZySwcW - Try it out! - https://ift.tt/3gMpYCl More results are available on our Instagram page! - https://ift.tt/2KBCNkT ❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: - https://ift.tt/2icTBUb - https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Let's Build a Language Translator! LIVE

The specific application of Machine Learning that has always interested me the most is Natural Language Processing. During this live game show, I'll ask 3 NLP questions that you'll need to answer interactively via a link i'll provide. At the end, we'll crown 1 winner. They'll win $500 cash (sent via BTC or ), a freestyle rap performance by me, and early access to my coming game titled Code Royale. If we can get computers to understand and interpret human language as well as we do, then they'll be capable of automating any intellectual task we can conceive of. Modern NLP curriculums incorporate probability, linear algebra, calculus, part linguistics, and even philosophy. We're going to build a language translator from English to Sanskrit using various deep learning tools and discuss different modern methodologies we could use. Please Subscribe! And Like. And Comment. That's what keeps me going. Answer live questions here: https://ift.tt/3k6XRzs Read through HuggingFace's NLP docs to prepare yourself and come Tuesday, let the games begin: https://ift.tt/2Q8vHe3 Learn Machine Learning in 3 Months for FREE: https://www.youtube.com/watch/Cr6VqTRO1v0 Best Language Model doc: https://ift.tt/2MfcKl4 Markov Chains: https://ift.tt/2UczaaD Best Reformer illustration: https://ift.tt/2tHg0Qk A collection of Sanskrit English projects to help you get started: https://ift.tt/38w0xEO This week's prize $ was sponsored by ClassPert (free search engine for courses): https://classpert.com/

Colorizing Strawberries is Hard…But Not For This AI! 🍓

❤️ Check out Weights & Biases and sign up for a free demo here: https://ift.tt/2YuG7Yf ❤️ Their report on this exact paper is available here: https://ift.tt/357IzXd 📝 The paper "Instance-aware Image Colorization" is available here: https://ift.tt/3bS6eek User study results: https://ift.tt/3eN9N8R DeOldify: https://ift.tt/2EVBb61 Follow them on Twitter for more! - https://twitter.com/deoldify 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Thumbnail background image credit: https://ift.tt/3eDh4HT Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

L6. LLuitant contra el sobre-entrenament - Xavier Giró - UPC ESEIAAT 2020

https://ift.tt/32OODCw L'objectiu de l'assignatura és el desenvolupament de xarxes neuronals profundes que permetin resoldre problemes d’intel·ligència artificial. Aquestes eines d’aprenentatge automàtic estimen els seus paràmetres a partir d’unes dades d’entrenament i un criteri d’optimització. L’assignatura presenta els tipus de capes més utilitzades en aquestes xarxes, així com els algoritmes i metodologies d’optimització més populars. Els estudiants seran capaços implementar-les en programari, així com monitoritzar el seu entrenament i diagnosticar quines accions poden millorar-ne el funcionament. El curs se centra en aplicacacions de xarxes neuronals profundes relacionades amb la gestió i distribució de senyals audiovisuals.

Com entrenar una xarxa neuronal - Xavier Giró - UPC ESEIAAT 2020

https://ift.tt/32OODCw L'objectiu de l'assignatura és el desenvolupament de xarxes neuronals profundes que permetin resoldre problemes d’intel·ligència artificial. Aquestes eines d’aprenentatge automàtic estimen els seus paràmetres a partir d’unes dades d’entrenament i un criteri d’optimització. L’assignatura presenta els tipus de capes més utilitzades en aquestes xarxes, així com els algoritmes i metodologies d’optimització més populars. Els estudiants seran capaços implementar-les en programari, així com monitoritzar el seu entrenament i diagnosticar quines accions poden millorar-ne el funcionament. El curs se centra en aplicacacions de xarxes neuronals profundes relacionades amb la gestió i distribució de senyals audiovisuals.

Let's Build Data Structures & Algorithms! LIVE

"Data Structures & Algorithms" is a subject every programmer needs to master in order pass coding interviews for big tech companies and write efficient code. I remember preparing for job interviews years ago by reading books like "Cracking the Coding Interview" and practicing on sites like LeetCode. I know that many of you are going through this right now. So in this 1 hour live game show, 1 winner will receive a $100 cash prize (in bitcoin) by following along as i solve several DS&A problems and answering 3 related questions interactively. I'll also freestyle a musical performance for them. Who will be the greatest programmer of them all and achieve Victory Royale? Find out this Friday at 8 AM PST/9:30 PM IST! Please Subscribe! And Like. And Comment. That's what keeps me going. Answer questions via: https://ift.tt/3k6XRzs

One Perceptron to Rule Them All: Language and Vision - Xavier Giró - ACM ICMR 2020 (Tutorial)

Giro-i-Nieto, X. One Perceptron to Rule Them All: Language, Vision, Audio and Speech. In Proceedings of the 2020 International Conference on Multimedia Retrieval (pp. 7-8). Slides: https://ift.tt/34vSrtA Deep neural networks have boosted the convergence of multimedia data analytics in a unified framework shared by practitioners in natural language, vision and speech. Image captioning, lip reading or video sonorization are some of the first applications of a new and exciting field of research exploiting the generalization properties of deep neural representation. This tutorial will firstly review the basic neural architectures to encode and decode vision, text and audio, to later review the those models that have successfully translated information across modalities.

AIDEN physio assistant by Shivay Lamba - Made With TensorFlow.js

In our 7th episode of Made With TensorFlow.js we head to India to meet Shivay Lamba who has created a virtual physio assistant to help you perform your daily exercises. With this system you can check you are doing the correct stretch using our PoseNet model live in the browser. AIDEN physio assistant Live Demo by Shivay Lamba → https://goo.gle/32DepJW Github Code → https://goo.gle/3mvxy8y Watch more of Made With TensorFlow.js → http://goo.gle/made-with-tfjs Subscribe to TensorFlow to stay up to date → https://goo.gle/TensorFlow #TensorFlow #TensorFlowJS #MadeWithTFJS #JavaScript #CreativeCoding #WebDev #PoseNet #BodyTracking #Exercise #Health #Wellbeing #Physio #Physiotherapy #Assistant

DeepMind Scholars: Benedetta's story

The DeepMind Scholars programme gives talented students from underrepresented backgrounds the support they need to study at leading universities, and connect with our researchers and engineers. Scholars get their Masters' fees paid in full, as well as guidance and support from personal DeepMind mentors. Find out more on our website: https://ift.tt/36afaLh

Towards RL that scales - Victor Campos - UPC TelecomBCN Barcelona 2020

Course site: https://ift.tt/34VAJ2w Towards RL that scales: Autonomous acquisition and transfer of knowledge ABSTRACT Designing agents that acquire knowledge autonomously and use it to solve new tasks efficiently is an important challenge in reinforcement learning (RL). Unsupervised learning provides a useful paradigm for autonomous acquisition of task-agnostic knowledge. In supervised settings, representations discovered through unsupervised pre-training offer important benefits when transferred to downstream tasks. In this talk, we discuss whether such techniques are well suited for RL. While reviewing recently proposed approaches for unsupervised pre-training of RL agents, we will gain insight on the key aspects that enable autonomous acquisition and efficient transfer of knowledge in our agents. BIO Víctor Campos holds a BsC and a MsC degrees in Electrical Engineering from Universitat Politècnica de Catalunya. He is currently pursuing his PhD on the intersection between Deep Learning and High Performance Computing at the Barcelona Supercomputing Center, supported by Obra Social "la Caixa" through La Caixa-Severo Ochoa International Doctoral Fellowship program. He has done internships at DFKI (2016), Columbia University (2017), Salesforce Research (2019), and Deepmind (2020). His research interests focus on scaling up deep learning and reinforcement learning methods to leverage compute and data.

This AI Creates A 3D Model of You! 🚶‍♀️

❤️ Check out Weights & Biases and sign up for a free demo here: https://ift.tt/2YuG7Yf ❤️ Their mentioned post is available here: https://ift.tt/2TSxDWO 📝 The paper "PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization" is available here: https://ift.tt/2AjZZTj 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. If you wish to support the series, click here: https://ift.tt/2icTBUb Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Inside TensorFlow - TF NumPy

In this episode of Inside TensorFlow, Software Engineers Ashish Agarwal and Peng Wang present TensorFlow NumPy. Ashish and Peng will discuss how you can accelerate NumPy using TensorFlow, and bring all the benefits of the TensorFlow ecosystem to NumPy! NumPy API on TensorFlow → https://goo.gle/2TMDi0Q Module: tf.experimental.numpy → https://goo.gle/2JvuDhi GitHub → https://goo.gle/3eiLUWg Add the Inside TensorFlow playlist → https://goo.gle/Inside-TensorFlow Subscribe to the TensorFlow channel → https://goo.gle/TensorFlow #InsideTensorFlow #TFNumPy #TensorFlow

Language Models are Open Knowledge Graphs (Paper Explained)

#ai #research #nlp Knowledge Graphs are structured databases that capture real-world entities and their relations to each other. KGs are usually built by human experts, which costs considerable amounts of time and money. This paper hypothesizes that language models, which have increased their performance dramatically in the last few years, contain enough knowledge to use them to construct a knowledge graph from a given corpus, without any fine-tuning of the language model itself. The resulting system can uncover new, unknown relations and outperforms all baselines in automated KG construction, even trained ones! PROMO - 3 Months Free TabNine Pro (sign up until 72 Hours after Video Launch): https://ift.tt/3oOjqbE (the site is a bit slow :) ) OUTLINE: 0:00 - Intro & Overview 1:40 - TabNine Promotion 4:20 - Title Misnomer 6:45 - From Corpus To Knowledge Graph 13:40 - Paper Contributions 15:50 - Candidate Fact Finding Algorithm 25:50 - Causal Attention Confusion 31:25 - More Constraints 35:00 - Mapping Facts To Schemas 38:40 - Example Constructed Knowledge Graph 40:10 - Experimental Results 47:25 - Example Discovered Facts 50:40 - Conclusion & My Comments Paper: https://ift.tt/3803IV7 Abstract: This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or semi-supervised manner, requiring humans to create knowledge. Recent deep language models automatically acquire knowledge from large-scale corpora via pre-training. The stored knowledge has enabled the language models to improve downstream NLP tasks, e.g., answering questions, and writing code and articles. In this paper, we propose an unsupervised method to cast the knowledge contained within language models into KGs. We show that KGs are constructed with a single forward pass of the pre-trained language models (without fine-tuning) over the corpora. We demonstrate the quality of the constructed KGs by comparing to two KGs (Wikidata, TAC KBP) created by humans. Our KGs also provide open factual knowledge that is new in the existing KGs. Our code and KGs will be made publicly available. Authors: Chenguang Wang, Xiao Liu, Dawn Song Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB Parler: https://ift.tt/38tQU7C LinkedIn: https://ift.tt/2Zo6XRA If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Who Wants to be a Code Millionaire? Ft. William Lin

William Lin is one of the world's all-time greatest competitive programmers. This champion is only 18 years old, got into MIT, and is already an International Grandmaster on CodeForces. I decided to invite him to my game show to test his skills by challenging him to a mixture of classic CP questions from CodeChef & novel Machine Learning CP questions. Will he be able to answer each one successfully? Can he win the 1MM point prize? Is Python better than C++? Find out in this episode, enjoy! Please Subscribe! And Like. And Comment. It means a lot to me. William Lin's Channel: https://www.youtube.com/channel/UCKuDLsO0Wwef53qdHPjbU2Q TWITTER: https://twitter.com/sirajraval INSTAGRAM: https://ift.tt/3mGI5x5 FACEBOOK: https://ift.tt/2hCqHdY EMAIL: hello@sirajraval.com Learn Machine Learning in 3 Months for free: https://www.youtube.com/watch?v=Cr6VqTRO1v0&t=0s&index=2&list=PLbPjwBfGhDfE0DZpUbVixr2SDDbhbM6Hg Learn Data Science in 3 Months for free: https://www.youtube.com/watch?v=9rDhY1P3YLA Learn Computer Science in 5 Months for free: https://www.youtube.com/watch?v=-OvRVlqKebI Learn NLP in 3 months for free: https://www.youtube.com/watch?v=GazFsfcijXQ Do you want to learn some of the most advanced topics in Computer Science fast and easily? Choose any one of the free educational playlists on my youtube channel, sit back, and feel the learn.

I Can Prove Our Universe is a Simulation 😌

The other day I got to thinking about modern computing & the Voyager 1 space probe, & I am pretty sure that if we can do this one thing, we can prove if we are living in a simulation or not... Outter Wilds Documentary: https://www.youtube.com/watch?v=LbY0mBXKKT0 The Space Game that I made: https://www.youtube.com/watch?v=iRk-Bha6uMw SUBSCRIBE FOR MORE: http://jabrils.com/yt WISHLIST MY VIDEO GAME: https://ift.tt/33NgHFz SUPPORT ON PATREON: https://ift.tt/2pZACkg JOIN DISCORD: https://ift.tt/2QkDa9O Please follow me on social networks: twitter: https://twitter.com/jabrils_ instagram: https://ift.tt/2QNVYvI REMEMBER TO ALWAYS FEED YOUR CURIOSITY