Deep Learning Theory [ICML Tutorial]

Join the channel membership: https://www.youtube.com/c/AIPursuit/join Subscribe to the channel: https://www.youtube.com/c/AIPursuit?sub_confirmation=1 Support and Donation: Paypal ⇢ https://paypal.me/tayhengee Patreon ⇢ https://www.patreon.com/hengee BTC ⇢ bc1q2r7eymlf20576alvcmryn28tgrvxqw5r30cmpu ETH ⇢ 0x58c4bD4244686F3b4e636EfeBD159258A5513744 Doge ⇢ DSGNbzuS1s6x81ZSbSHHV5uGDxJXePeyKy Earn up to $170 welcome bonus on Huobi now with my crypto affiliate link: Binance ⇢ https://accounts.binance.com/en/register?ref=27700065 Huobi ⇢ https://www.huobi.com/en-us/topic/welcome-bonus/?invite_code=xj9pc The video is reposted for educational purposes and encourages involvement in the field of research. Source: https://slideslive.com/38917405/deep-learning-theory 1. Complexity of Linear Regions in Deep Networks 2. On Connected Sublevel Sets in Deep Learning 3. Adversarial Examples Are a Natural Consequence of Test Error in Noise 4. Greedy Layerwise Learning Can Scale To ImageNet 5. On the Impact of the Activation function on Deep Neural Networks Training 6. Estimating Information Flow in Deep Neural Networks 7. The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects 8. Characterizing Well-Behaved vs. Pathological Deep Neural Networks 9. Understanding Geometry of Encoder-Decoder CNNs 10. Traditional and Heavy Tailed Self Regularization in Neural Network Models