Agent57: Outperforming the Atari Human Benchmark

DeepMind's Agent57 is the first RL agent to outperform humans in all 57 Atari benchmark games. It extends previous algorithms like Never Give Up and R2D2 by meta-learning the exploration-exploitation tradeoff controls. https://ift.tt/39xTXKX https://ift.tt/3aIfim0 Abstract: Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algorithms. Previous work has achieved good average performance by doing outstandingly well on many games of the set, but very poorly in several of the most challenging games. We propose Agent57, the first deep RL agent that outperforms the standard human benchmark on all 57 Atari games. To achieve this result, we train a neural network which parameterizes a family of policies ranging from very exploratory to purely exploitative. We propose an adaptive mechanism to choose which policy to prioritize throughout the training process. Additionally, we utilize a novel parameterization of the architecture that allows for more consistent and stable learning. Authors: Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Charles Blundell Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB

Is Visualizing Light Waves Possible? ☀️

❤️ Check out Weights & Biases here and sign up for a free demo here: https://ift.tt/2YuG7Yf Their blog post is available here: https://ift.tt/2uLfOzJ 📝 The paper "Progressive Transient Photon Beams" is available here: https://ift.tt/2V3IkX1 📝 The paper "Femto-Photography: Capturing and Visualizing the Propagation of Light" is available here: https://ift.tt/33WLOyu My light transport course is available here: https://ift.tt/2rdtvDu The paper with the image of the shown caustics is available here: https://ift.tt/2kEcw8R  🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m

TensorFlow Lite for Microcontrollers (TF Dev Summit '20)

TensorFlow Lite for Microcontrollers or TFLite Micro is designed to run machine learning models on microcontrollers and other embedded devices. The key advantages are low energy consumption, small size, network connectivity is not required, privacy by running inference on-device and a large scale impact as billions of microcontrollers are embedded within hardware every year. In this video, we demostrate running a tiny ~250KB binary image classification model which detects if a person is present in the image captured by the SparkFunEdge microcontroller (https://goo.gle/3auscnH). If the microcontroller detects a person, the green LED lights up; otherwise the orange LED lights up. Every time it runs an inference, the blue LED toggles. Speakers: Meghna Natraj - Software Engineer Pete Warden - Staff Software Engineer Jason Mayes - Senior Developer Advocate Here are some resources to get started: Website → https://goo.gle/2yiYyUl Github → https://goo.gle/2UsBkDW Examples (generate a sine wave, person detection, simple audio recognition, magic wand) → https://goo.gle/3dGu3rq Advanced resources: TinyML Book → https://goo.gle/2JqBZPI Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow

Fairness Indicators for TensorFlow (TF Dev Summit '20)

Within this TensorFlow Dev Summit demo we will explore two case studies using Fairness Indicators. The first notebook demonstrates an easy way to create and optimize constrained problems using the TFCO library. This method can be useful in improving models when we find that they’re not performing equally well across different slices of our data, which we can identify using Fairness Indicators. Second, we will use Fairness Indivatores with the larger TensorFlow Ecosystem to show how Machine Learning Metadata (MLMD) and the lineage tracking ability can be useful for fairness while working in TensorFlow Extended (TFX). Speakers: Thomas Greenspan - Software Engineer Sean O'Keefe - Software Engineer Jason Mayes - Senior Developer Advocate Resources: Fairness Indicators Lineage Case Study → https://goo.gle/3avg3in Fairness Indicators and TF Constrained Optimization Case Study → https://goo.gle/3bxAgnR TensorFlow Constrained Optimization → https://goo.gle/2WUp5RV FAT* Understanding the Context and Consequences of Pre-trial Detention → https://goo.gle/2ydC0Eh Partnership on AI: Report on Algorithmic Risk Assessment Tools in the U.S. Criminal Justice System → https://goo.gle/2JnnBIf Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow

TensorFlow.js (TF Dev Summit '20)

TensorFlow.js allows you to use machine learning anywhere that JavaScript can run - which is pretty much everywhere! Check out our latest easy to use machine learning models we launched this year: 1. FaceMesh which can detect 486 points on a human face in real time enabling AR or whatever creative idea you may have. 2. HandPose - which can track 21 unique points of a human hand enabling you to recognize a gesture for example 3. Mobile BERT - cutting edge natural language processing model can now be used in the browser to answer questions about any piece of text you pass it. Speakers: Jason Mayes - Senior Developer Advocate Ewa Matejska - Technical Program Manager Resources: Learn more about Face Mesh and Hand Pose here → https://goo.gle/2WTCwSc Learn more about Mobile Bert here → https://goo.gle/3atbSnh To get started with TensorFlow.js check out our website (https://goo.gle/2XLhMe0), or find us on Glitch (https://goo.gle/2WUuhp4) and CodePen (https://goo.gle/2JoH0bE) to fork ready to run examples! Tag us with anything you create for a chance to be featured at future events using #MadeWithTFJS on social media. FaceMesh Model → https://goo.gle/2xAuR0s HandPose Model → https://goo.gle/2QUubtP BERT Q&A Model → https://goo.gle/2JqBrt7 Learn more about TF.js → https://goo.gle/2XLhMe0 Use #MadeWithTFJS on social to show us what you make! Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow

Axial Attention & MetNet: A Neural Weather Model for Precipitation Forecasting

MetNet is a predictive neural network model for weather prediction. It uses axial attention to capture long-range dependencies. Axial attention decomposes attention layers over images into row-attention and column-attention in order to save memory and computation. https://ift.tt/2ybtXIp https://ift.tt/36be9RR Abstract: Weather forecasting is a long standing scientific challenge with direct social and economic impact. The task is suitable for deep neural networks due to vast amounts of continuously collected data and a rich spatial and temporal structure that presents long range dependencies. We introduce MetNet, a neural network that forecasts precipitation up to 8 hours into the future at the high spatial resolution of 1 km2 and at the temporal resolution of 2 minutes with a latency in the order of seconds. MetNet takes as input radar and satellite data and forecast lead time and produces a probabilistic precipitation map. The architecture uses axial self-attention to aggregate the global context from a large input patch corresponding to a million square kilometers. We evaluate the performance of MetNet at various precipitation thresholds and find that MetNet outperforms Numerical Weather Prediction at forecasts of up to 7 to 8 hours on the scale of the continental United States. Authors: Casper Kaae Sønderby, Lasse Espeholt, Jonathan Heek, Mostafa Dehghani, Avital Oliver,Tim Salimans, Shreya Agrawal, Jason Hickey, Nal Kalchbrenner Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB

Everybody Can Make DeepFakes Now!

❤️ Check out Weights & Biases here and sign up for a free demo here: https://ift.tt/2YuG7Yf Their blog post is available here: https://ift.tt/2u2vEG4 📝 The paper "First Order Motion Model for Image Animation" and its source code are available here: https://ift.tt/35psoRV Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m #DeepFakes

GAN Compression

This video explains the paper "GAN Compression: Efficient Architectures for Interactive Conditional GANs"! This technique adapts Knowledge Distillation for the GAN framework by copying intermediate features from the teacher to student generator, transferring the pre-trained teacher discriminator, and structuring image-to-image translation problems in the "paired" setting by using the teacher generator image as the ground truth image. This paper also explores the use of One-Shot Neural Architecture Search to find an efficient architecture for the student generator network! Thanks for watching, Please Subscribe! Paper Links: GAN Compression: https://ift.tt/2QLxjIg GAN Compression Video Demo from Authors: https://www.youtube.com/watch?v=31AhcLqWc68&list=PL80kAHvQbh-r5R8UmXhQK1ndqRvPNw_ex&index=3&t=0s Pix2Pix: https://ift.tt/2kPCvgx CycleGAN: https://ift.tt/2opD3rk GauGAN: https://ift.tt/2CsbLsZ AVID: https://ift.tt/2xoCvLo DermGAN: https://ift.tt/2vwCAMt SimGAN: https://ift.tt/2ohC3bJ MobileNets: https://ift.tt/2o1bEiR One-Shot Neural Architecture Search: https://ift.tt/2JgmmdK Intro Music: "Runs" from Unminus Thanks for watching! Please Subscribe!

Can Self-Driving Cars Learn Depth Perception? 🚘

❤️ Check out Weights & Biases here and sign up for a free demo here: https://ift.tt/2YuG7Yf The showcased instrumentation post is available here: https://ift.tt/3dqc0G9 📝 The paper "Unsupervised Learning of Depth and Ego-Motion from Video" is available here: https://ift.tt/2qebod5  🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m

Google’s Chatbot: Almost Perfect

❤️ Check out Lambda here and sign up for their GPU Cloud: https://ift.tt/35NkCT7 📝 The paper "Towards a Human-like Open-Domain Chatbot" is available here: https://ift.tt/2Gs7FTx ❤️ 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: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m

Scaling Tensorflow data processing with tf.data (TF Dev Summit '20)

As model training becomes more distributed in nature, tf.data has evolved to be more distribution aware and performant. This talk presents tf.data tools for scaling TensorFlow data processing. In particular: tf.data service that allows your tf.data pipeline to run on a cluster of machines, and tf.data.snapshot that materializes the results to disk for reuses across multiple invocations. Speaker: Rohan Jain - Staff Software Engineer Resources: GitHub Distributed tf.data service → https://goo.gle/2VrYDi2 tf.data: Build TensorFlow input pipelines → https://goo.gle/2VTnnjk Better performance with the tf.data API → https://goo.gle/38wyKAy GitHub tf.data snapshot → https://goo.gle/2v42Ai8 Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow

Enhanced POET: Open-Ended Reinforcement Learning

This video will explain details behind the new Enhanced POET algorithm from Uber AI Labs! This is a really exciting algorithm for the co-evolution of agents and the environments they learn in! Extensions in this paper make the framework applicable to more general Machine Learning problems after being originally proven on Bipedal Walking agents. A very interesting finding from this study is that agents cannot be optimized from scratch to solve the complex environments that arise out of this co-evolution! Thanks for watching! Please Subscribe! Paper Links: Enhanced POET: https://ift.tt/2J4X81K Original POET: https://ift.tt/2xUnFwp Generative Teaching Networks: https://ift.tt/2w8Yd64 Learning to Continually Learn: https://ift.tt/2VG7dKi Thanks for watching! Please Subscribe!

Semantic Pyramid for Image Generation

This video explores a new GAN model for generating images by conditioning them on features from pre-trained image classifiers! This is really interesting for visualizing what is contained in pre-trained image classifiers as well as controllable image editing. The authors also show that this can be used for semantic image composition such as copying a tree and pasting it into a snow landscape or image relabeling by changing the embedded logit from the pre-trained classifier to produce an image of a new class while retaining as much of the original image as possible. Thanks for watching! Please Subscribe! Paper Links: Semantic Pyramid for Image Generation: https://ift.tt/396KOsF Corresponding Github Page: https://ift.tt/2IZbAbw Neural Style Transfer: https://ift.tt/2kNfxFU Zoom In: An Introduction to Circuits: https://ift.tt/39EOZgn EfficientDet: https://ift.tt/2xQJ7m7 Generative Teaching Networks: https://ift.tt/2w8Yd64 DermGAN: https://ift.tt/2vwCAMt Classification Accuracy Score for Conditional Generative Models: https://ift.tt/2U1fmaU GauGAN: https://ift.tt/2CsbLsZ SinGAN: https://ift.tt/2WnPSG5 StyleGAN2 Distillation: https://ift.tt/2IDaKRK Semi-Supervised StyleGAN for Disentanglement Learning: https://ift.tt/3b5VfxN Thanks for watching! Please Subscribe!

This Neural Network Regenerates…Kind Of!

❤️ Check out Weights & Biases here and sign up for a free demo here: https://ift.tt/2YuG7Yf The shown blog post is available here: https://ift.tt/2okfRiO 📝 The paper "Growing Neural Cellular Automata" is available here: https://ift.tt/2ShegXn Game of Life source: https://copy.sh/life/  🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m

This Neural Network Learned The Style of Famous Illustrators

❤️ Check out Weights & Biases here and sign up for a free demo here: https://ift.tt/2YuG7Yf The shown blog post is available here: https://ift.tt/2QgzovF 📝 The paper "GANILLA: Generative Adversarial Networks for Image to Illustration Translation" is available here: https://ift.tt/3bARwJM 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Thumbnail background image credit: https://ift.tt/2vYZCfo Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m

Responsible AI with TensorFlow (TF Dev Summit '20)

Introducing a framework to think about ML, fairness and privacy. This talk will propose a fairness-aware ML workflow, illustrate how TensorFlow tools such as Fairness Indicators can be used to detect and mitigate bias, and will then transition to a specific case-study regarding privacy that will walk participants through a couple of infrastructure pieces that can help train a model in a privacy preserving manner. Speakers: Catherina Xu - Associate Product Manager Miguel Guevara - Product Manager Resources: TensorFlow Federated → https://goo.gle/2PtAp2f GitHub TF Federated → https://goo.gle/2wYBWb5 GitHub TF Privacy → https://goo.gle/2I7XpRg Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow

AlphaGo - The Movie | Full Documentary

With more board configurations than there are atoms in the universe, the ancient Chinese game of Go has long been considered a grand challenge for artificial intelligence. On March 9, 2016, the worlds of Go and artificial intelligence collided in South Korea for an extraordinary best-of-five-game competition, coined The DeepMind Challenge Match. Hundreds of millions of people around the world watched as a legendary Go master took on an unproven AI challenger for the first time in history. Directed by Greg Kohs with an original score by Academy Award nominee, Hauschka, AlphaGo chronicles a journey from the halls of Oxford, through the backstreets of Bordeaux, past the coding terminals of DeepMind in London, and ultimately, to the seven-day tournament in Seoul. As the drama unfolds, more questions emerge: What can artificial intelligence reveal about a 3000-year-old game? What can it teach us about humanity?

Learning to read with TensorFlow and Keras (TF Dev Summit '20)

Natural Language Processing (NLP) has hit an inflection point, and this talk shows you how TensorFlow and Keras make it easy to preprocess, train, and hypertune text models. Speaker: Paige Bailey - Product Manager Resources: The Goldilocks Principle → https://goo.gle/2PPUmBi GitHub Keras Preprocessing Layers → https://goo.gle/2uWFqKm GitHub Keras Preprocessing API → https://goo.gle/38ohwoU Understanding Encoder-Decoder Sequence to Sequence Model → https://goo.gle/2IsPtde Keras Tuner documentation → https://goo.gle/2InBK7J Hyperparameter tuning with Keras Tuner → https://goo.gle/2VPtMvR TensorFlow Text → https://goo.gle/2TueZVV GitHub Bert → https://goo.gle/2xhNQgm TensorFlow Hub breakdown → https://goo.gle/2wAwbQy Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow

TensorFlow Dev Summit 2020 Keynote

Join the TensorFlow team as they kick-off the 2020 TensorFlow Dev Summit. The keynote will feature new product updates for the TensorFlow ecosystem. Speakers: Megan Kacholia - VP, Engineering Manasi Joshi - Engineering Director Kemal El Moujahid - Director, Product Management Resources: Start a TFUG  → https://goo.gle/38NCpKx Join a Special Interest Group → https://goo.gle/39TRcVn Apply for Google Summer of Code → https://goo.gle/2TK1e5M Compete on Kaggle → https://goo.gle/3cP2yM7 Responsible AI Dev Post Challenge → https://goo.gle/2Q6vyoO Machine Learning Crash Course → https://goo.gle/338YH8d Take a specialization course → https://goo.gle/2IDifYL Submit a proposal for an ML course → https://goo.gle/38NCNIZ Get certified  → https://goo.gle/39MVNZe Watch all TensorFlow Dev Summit 2020 sessions → https://goo.gle/TFDS20 Subscribe to the TensorFlow YouTube channel → https://goo.gle/TensorFlow

Deformable Simulations…Running In Real Time!

❤️ Check out Weights & Biases here and sign up for a free demo here: https://ift.tt/2YuG7Yf The shown blog post is available here: https://ift.tt/339uzcB 📝 The paper "A Scalable Galerkin Multigrid Method for Real-time Simulation of Deformable Objects" is available here: https://ift.tt/2xrvp93 ❤️ 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: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m

Coronavirus Competition Results (Remdesivir)

I’m pleased to announce the results of our open-source Coronavirus Drug Discovery Competition! In just 2 weeks, hundreds of developers from around the world signed up to join the fight against the novel coronavirus, using publicly available datasets and algorithms to come up with relevant solutions. The top 3 submissions, winning $3500 in prizes, stood out from the rest in terms of their algorithmic and reporting quality. In this episode, I’m going to announce each of their backgrounds, as well as dive into the various machine learning techniques they used to predict a suitable treatment for Coronavirus. The top submission identified a compound called Remdesivir as the the most promising treatment for COVID-2019, due to its high scoring inhibitory potential when docked against the Coronavirus main Protease. Remdesivir was recently shown to be effective in treating the first US patient infected with COVID-2019, but is currently undergoing clinical trials to gain FDA approval. These findings help confirm it’s potential as an effective COVID-2019 treatment. I’ll explain more in the vid, Enjoy! Winning Submissions Announcement blog-post: https://ift.tt/2PUJ92w Matt O’Connor (1st place): https://ift.tt/38Bcoxz Thomas MacDougall (2nd Place): https://ift.tt/3aEQjjs Tinka Vidovic (3rd Place): https://ift.tt/2VXgGNd Subscribe for more educational videos! It means a lot to me. TWITTER: https://bit.ly/2OHYLbB WEBSITE: https://bit.ly/2OoVPQF INSTAGRAM: https://bit.ly/312pLUb FACEBOOK: https://bit.ly/2OqOhx1 Original Coronavirus Competition Video: https://www.youtube.com/watch?v=1LJgkovowgA Are you a total beginner to machine learning? Watch this: https://www.youtube.com/watch?v=Cr6VqTRO1v0 Learn Python: https://www.youtube.com/watch?v=T5pRlIbr6gg Signup for my newsletter for exciting updates in the field of AI: https://goo.gl/FZzJ5w Credits: Coronavirus Drug Discovery competitors Github open-source community Scientific American Image assets are from across the Web Hit the Join button above to sign up to become a member of my channel for access to exclusive live streams! And please support me on Patreon: https://ift.tt/2cMCk13

Transferring Real Honey Into A Simulation 🍯

❤️ Check out Linode here and get $20 free credit on your account: https://ift.tt/2LaDQJb 📝 The paper "Video-Guided Real-to-Virtual Parameter Transfer for Viscous Fluids" is available here: https://ift.tt/2PTSvLZ ❤️ 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: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m

Train Large, Then Compress

This video explains a new study on the best way to use a limited compute budget when training Natural Language Processing tasks. They show that Large models reach a lower error faster than smaller models and stopping training early with large models achieves better performance than longer training with smaller models. These larger models come with an inference bottleneck, it takes longer to make predictions and costs more to store these weights. The authors alleviate the inference bottleneck by showing that these larger models are robust to compression techniques like quantization and pruning! Thanks for watching, Please Subscribe! Paper Links: Train Large, Then Compress: https://ift.tt/3awfC74 BAIR Blog Post: https://ift.tt/2ImJYNl What is Gradient Accumulation in Deep Learning? https://ift.tt/30M4f7o Transfer Learning in NLP: https://ift.tt/2VPiWpR SST: https://ift.tt/2t56jGq MNLI: https://ift.tt/2PW2HUe The Lottery Ticket Hypothesis: https://ift.tt/2PTd4pv GPT: https://ift.tt/2HeACni

Can Neural Image Generators Be Detected?

❤️ Check out Weights & Biases here and sign up for a free demo here: https://ift.tt/2YuG7Yf Their instrumentation of this paper: https://ift.tt/39jebIZ 📝 The paper "CNN-generated images are surprisingly easy to spot...for now" is available here: https://ift.tt/32DPXGW Our Discord server is now available here and you are all invited! https://ift.tt/2IfLukp 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh. https://ift.tt/2icTBUb Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/karoly_zsolnai Web: https://ift.tt/1NwkG9m #DeepFake #DeepFakes

Training a model to recognize sentiment in text (NLP Zero to Hero, part 3)

Welcome to Zero to Hero for Natural Language Processing using TensorFlow! If you’re not an expert on AI or ML, don’t worry -- we’re taking the concepts of NLP and teaching them from first principles with our host Laurence Moroney (@lmoroney). In the last couple of episodes you saw how to tokenize text into numeric values and how to use tools in TensorFlow to regularize and pad that text. Now that we’ve gotten the preprocessing out of the way, we can next look at how to build a classifier to recognize sentiment in text. Links: Colab → https://goo.gle/tfw-sarcembed GitHub → https://goo.gle/2PH90ea Coding TensorFlow → https://goo.gle/2Y43cN4 Subscribe to the TensorFlow channel → https://goo.gle/TensorFlow

The Hardest Kaggle Challenge

There's a new $20,000 challenge on Kaggle that uses a dataset titled "The Abstraction and Reasoning Corpus". The aim of this episode is to get you up to speed as fast as possible so that you can participate. This challenge is hosted by Francois Chollet, the creator of the popular deep learning library Keras, and there are still 3 months to go. The goal is to create an algorithm that can learn the relationship between input-output pairs of colored tiles. Sounds simple at first, but upon closer inspection, creating an algorithm that's able to do so given such a small dataset requires genuine AI innovation. Deep Learning won't work because it requires big datasets and expensive compute, so even though this challenge is difficult, it's also the most accessible! We'll be learning about the dataset, related paper, and the various techniques that Kagglers have already attempted. Then, we'll learn about Neural Program Synthesis and future directions that could ultimately solve this problem. Enjoy! Subscribe for more educational videos! It means a lot to me. TWITTER: https://bit.ly/2OHYLbB WEBSITE: https://bit.ly/2OoVPQF INSTAGRAM: https://bit.ly/312pLUb FACEBOOK: https://bit.ly/2OqOhx1 Kaggle Challenge: https://ift.tt/2SqHIKK ARC Dataset: https://ift.tt/2oSNQ2o Convolutional Network Kernel: https://ift.tt/32HnqAh Cellular Automata Kernel: https://ift.tt/2HAcYAN Genetic Algorithm Kernel: https://ift.tt/2VnWCDD Really great paper on Neural Program Synthesis: https://ift.tt/2G0hiq9 Intro to Convolutional Networks: https://www.youtube.com/watch?v=FTr3n7uBIuE Intro to Genetic Algorithms: https://www.youtube.com/watch?v=9zfeTw-uFCw Intro to Cellular Automata: https://www.youtube.com/watch?v=DKGodqDs9sA Simple PointerNet example: https://ift.tt/3ap05pM Hit the Join button above to sign up to become a member of my channel for access to exclusive live streams! Signup for my newsletter for exciting updates in the field of AI: https://goo.gl/FZzJ5w Credits: Kaggle & Kagglers Francois Chollet Google Image Search for the image assets And please support me on Patreon: https://ift.tt/2cMCk13

BERT Can See Out of the Box

The video explores an interesting paper seeing how easily (w.r.t fine-tuning effort) pre-trained visual embeddings can be combined with text captions for visual question generation in the BERT model. This video explores the approach the authors take for this, applications of vision-language models, and question generation. Thanks for watching! Please Subscribe! Paper Links: BERT Can See Out of the Box: https://ift.tt/3ar15K1 BERT: https://ift.tt/2pMXn84 ImageBERT: https://ift.tt/398zzAe Training QA Models from Synthetic Data: https://ift.tt/2VB8nX9 AI2 BREAK: https://ift.tt/2PG7cSD Google Street View Panoramas for Language Grounding Tasks: https://ift.tt/2SYlgJj Google Open Images V6 with Localized Narratives: https://ift.tt/2SYlgJj Salesforce Learning Reasoning Paths: https://ift.tt/32pAB8N Thanks for Watching! Please Subscribe!