Lecture 1.1 — Why do we need machine learning — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.2 — What are neural networks — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.3 — Some simple models of neurons — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.4 — A simple example of learning — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.5 — Three types of learning — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.1 — Types of neural network architectures — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.2 — Perceptrons first generation neural networks — [ Deep Learning | Hinton | UofT ] Lecture 2.3 — A geometrical view of perceptrons — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.4 — Why the learning works — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.5 — What perceptrons cant do — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.1 — Learning the weights of a linear neuron — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.2 — The error surface for a linear neuron — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.3 — Learning weights of logistic output neuron — [ Deep Learning | Hinton | UofT ] Lecture 3.4 — The backpropagation algorithm — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.5 — Using the derivatives from backpropagation — [ Deep Learning | Hinton | UofT ] Lecture 4.1 — Learning to predict the next word — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.2 — A brief diversion into cognitive science — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.3 — The softmax output function — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.4 — Neuro probabilistic language models — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.5 — Dealing with many possible outputs — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.1 — Why object recognition is difficult — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.2 — Achieving viewpoint invariance — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.3 — Convolutional nets for digit recognition — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.4 — Convolutional nets for object recognition — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 6.1 — Overview of mini batch gradient descent — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 6.2 — A bag of tricks for mini batch gradient descent — [ Deep Learning | Hinton | UofT ] Lecture 6.3 — The momentum method Neural — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 6.4 — Adaptive learning rates for each connection — [ Deep Learning | Hinton | UofT ] Lecture 6 5 — Rmsprop normalize the gradient — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 7.1 — Modeling sequences a brief overview — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 7.2 — Training RNNs with back propagation — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 7.3 — A toy example of training an RNN — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 7.4 — Why it is difficult to train an RNN — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 7.5 — Long term Short term memory — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 8.1 — A brief overview of Hessian free optimization — [ Deep Learning | Hinton | UofT ] Lecture 8.2 — Modeling character strings — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 8.3 — Predicting the next character using HF — [ Deep Learning | Hinton | UofT ] Lecture 8.4 — Echo State Networks — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 9.1 — Overview of ways to improve generalization — [ Deep Learning | Hinton | UofT ] Lecture 9.2 — Limiting the size of the weights — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 9.3 — Using noise as a regularizer — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 9.4 — Introduction to the full Bayesian approach — [ Deep Learning | Hinton | UofT ] Lecture 9.5 — The Bayesian interpretation of weight decay — [ Deep Learning | Hinton | UofT ] Lecture 9.6 — MacKay s quick and dirty method — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 10.1 — Why it helps to combine models — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 10.2 — Mixtures of Experts — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 10.3 — The idea of full Bayesian learning — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 10.4 — Making full Bayesian learning practical — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 10.5 — Dropout — [ Deep Learning | Geoffrey Hinton | Toronto ] Lecture 11.1 — Hopfield Nets — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.1 — Why do we need machine learning — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.2 — What are neural networks — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.3 — Some simple models of neurons — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.4 — A simple example of learning — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 1.5 — Three types of learning — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.1 — Types of neural network architectures — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.2 — Perceptrons first generation neural networks — [ Deep Learning | Hinton | UofT ] Lecture 2.3 — A geometrical view of perceptrons — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.4 — Why the learning works — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 2.5 — What perceptrons cant do — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.1 — Learning the weights of a linear neuron — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.2 — The error surface for a linear neuron — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.3 — Learning weights of logistic output neuron — [ Deep Learning | Hinton | UofT ] Lecture 3.4 — The backpropagation algorithm — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 3.5 — Using the derivatives from backpropagation — [ Deep Learning | Hinton | UofT ] Lecture 4.1 — Learning to predict the next word — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.2 — A brief diversion into cognitive science — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.3 — The softmax output function — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.4 — Neuro probabilistic language models — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 4.5 — Dealing with many possible outputs — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.1 — Why object recognition is difficult — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.2 — Achieving viewpoint invariance — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.3 — Convolutional nets for digit recognition — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 5.4 — Convolutional nets for object recognition — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 6.1 — Overview of mini batch gradient descent — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 6.2 — A bag of tricks for mini batch gradient descent — [ Deep Learning | Hinton | UofT ] Lecture 6.3 — The momentum method Neural — [ Deep Learning | Geoffrey Hinton | UofT ] Lecture 6.4 — Adaptive learning rates for each connection — [ Deep Learning | Hinton | UofT ]