VS298 (Fall 06): Schedule: Difference between revisions
From RedwoodCenter
Jump to navigationJump to search
| Line 3: | Line 3: | ||
*'''Week 1 (Sept. 6,8)''': Introduction; theory and modeling in neuroscience; linear neuron models; perceptron | *'''Week 1 (Sept. 6,8)''': Introduction; theory and modeling in neuroscience; linear neuron models; perceptron | ||
*'''Week 2 (Sept. 13,15)''': guest lecture (Bell) | *'''Week 2 (Sept. 13,15)''': guest lecture (Bell, Wednesday only) | ||
*'''Week 3 (Sept. 20, 22)''': Perceptron learning rule; Widrow-Hoff rule; Objective functions and gradient descent; Multilayer networks and backpropagation | *'''Week 3 (Sept. 20, 22)''': Perceptron learning rule; Widrow-Hoff rule; Objective functions and gradient descent; Multilayer networks and backpropagation | ||
| Line 9: | Line 9: | ||
*'''Week 4 (Sept. 27, 29)''': Reinforcement learning; Theory of associative reward-penalty; Models and critics | *'''Week 4 (Sept. 27, 29)''': Reinforcement learning; Theory of associative reward-penalty; Models and critics | ||
*'''Week 5 (Oct. 4, 6)''': guest lecture (Russell) | *'''Week 5 (Oct. 4, 6)''': guest lecture (Russell, Wednesday only) | ||
*'''Week 6 (Oct. 11, 13)''': Unsupervised learning; Hebbian learning and PCA; winner-take-all networks and clustering; sparse, distributed coding | *'''Week 6 (Oct. 11, 13)''': Unsupervised learning; Hebbian learning and PCA; winner-take-all networks and clustering; sparse, distributed coding | ||
Revision as of 04:42, 9 September 2006
Schedule
- Week 1 (Sept. 6,8): Introduction; theory and modeling in neuroscience; linear neuron models; perceptron
- Week 2 (Sept. 13,15): guest lecture (Bell, Wednesday only)
- Week 3 (Sept. 20, 22): Perceptron learning rule; Widrow-Hoff rule; Objective functions and gradient descent; Multilayer networks and backpropagation
- Week 4 (Sept. 27, 29): Reinforcement learning; Theory of associative reward-penalty; Models and critics
- Week 5 (Oct. 4, 6): guest lecture (Russell, Wednesday only)
- Week 6 (Oct. 11, 13): Unsupervised learning; Hebbian learning and PCA; winner-take-all networks and clustering; sparse, distributed coding
- Week 7 (Oct. 18, 20): Plasticity and cortical maps; Self-organizing maps; Kohonen nets; Models of experience dependent learning and cortical reorganization
- Week 8 (Oct. 25, 27): Recurrent networks; attractor dynamics; Hopfield networks, Pattern completion; Line attractors and `bump circuits’
- Week 9 (Nov. 1, 3): Associative memory models
- Week 10 (Nov. 8, 10): Probabilistic models and inference; The mixture of Gaussians model
- Week 11 (Nov. 15, 17): Boltzmann machines
- Week 12 (Nov. 22, 24): Sparse coding and ICA
- Week 13 (Nov. 29, Dec. 1): Neural implementations; Integrate-and-fire model; Neural encoding and decoding; Limits of precision in neurons
- Week 14 (Dec. 6, 8): Special topics; student projects
