1. Outline
1.1. neurons
1.1.1. basic structure
1.1.2. membrane potentials and channels
1.1.3. dendritic computations
1.1.4. generation and propagation of the action potential
1.1.5. structure and function of synapses
1.2. associative memories
1.2.1. Willshaw's associative memory
1.2.2. Hopfield networks
1.2.3. Linear Associative Memories
1.3. computation with neurons
1.3.1. linear threshold units
1.3.2. constructing boolean circuits out of neurons
1.3.3. dynamic computations with networks of neurons
1.3.4. rule 110, Turing equivalence
1.3.5. Hebb's rule
1.4. classification and learning
1.4.1. linear threshold units and perceptron learning algorithms
1.4.2. logistic regression and gradient descent
1.4.3. multi-layer perceptrons and backpropagation
1.4.4. posterior probabilities and multilayer perceptrons
1.4.5. PCA and "neural" PCA
1.4.6. k-means algorithm, EM algorithms, SOM
1.4.7. gradient descent version of k-means
1.4.8. convolutional neural networks
1.4.9. multilayer convolutional neural networks
1.5. visual object recognition
1.5.1. feature hierarchies
1.5.2. convolutional neural networks
1.5.3. the HMAX model
1.5.4. experimental results on databases
1.5.5. view-based or component based recognition
1.5.6. experiments and theory by Bulthoff
1.5.7. experiments and theory by Biederman
1.5.8. attention, salience, grouping
1.6. theory
1.6.1. Bayesian decision theory
1.6.2. loss functions
1.6.3. risk minimization
1.6.4. Bayesian parameter estimation
1.6.5. ML, MAP, Bayesian methods
1.6.6. game theory
1.6.7. agent theory
1.6.8. evolution