## BCSC 512: Schedule

Only students who are enrolled in the course may access the course readings online. You must be logged into Blackboard to download these materials.

A **rough** outline of the course is as follows:

- Class 1
- Introduction / Organization

Introduction to Hebbian learning - Read lecture slides on Hebbian Learning I

Read "The Appeal of Parallel Distributed Processing" by McClelland, Rumelhart, and Hinton - Class 2
- Linear algebra
- Read lecture slides on Hebbian Learning II

Read "An Introduction to Linear Algebra in Parallel Distributed Processing" by Jordan - Class 3
- Supervised Hebbian learning
- Read lecture slides on Hebbian Learning II

Read "An Introduction to Linear Algebra in Parallel Distributed Processing" by Jordan - Class 4
- Unsupervised Hebbian learning
- Read lecture slides on Hebbian Learning III

Read note titled "Variance, Covariance, Correlation, and Correlation Coefficient"

Read note titled "Principal Components Analysis"

Read note titled "Principal Components Analysis and Unsupervised Hebbian Learning"

Read A Tutorial on "Principal Component Analysis" by Shlens - ***Distribute Homework #1 (due two weeks after distribution)
- Class 5
- Student presentation of papers
- Read "Categorization and Selective Neurons" by Anderson and Mozer

Read "Eigenfaces for Recognition" by Turk and Pentland - Class 6
- Probability theory
- Read lectures slides on Probability and Visual Perception

Read "Probability Theory and Classical Statistics" by Lynch

Read note titled "Gaussian, Bernoulli, and Multinomial Distributions" - Class 7
- Probability theory
- Read lecture slides on Probability and Visual Perception

Read "Probability Theory and Classical Statistics" by Lynch

Read note titled "Gaussian, Bernoulli, and Multinomial Distributions" - Class 8
- Read lecture slides on Practice Probability Problems
- Class 9
- Statistical inference
- Read lecture slides on Statistical Estimation

Read Tutorial on "Maximum Likelihood Estimation" by Myung - Class 10
- Read lecture slides on Implementing Probabilistic Processing Using Python
- Class 11
- Introduction to deep neural networks I
- Read lecture slides on Neural Networks I
- Class 12
- Introduction to deep neural networks I (continued)

Introduction to deep neural networks II - Read lecture slides on Neural Networks I

Read lecture slides on Neural Networks II - Class 13
- Introduction to deep neural networks II (continued)
- Read lecture slides on Neural Networks II
- Class 14
- Introduction to deep neural networks III
- Read lecture slides on Neural Networks III

Read note titled "Backpropagation Algorithm" - ***Distribute Homework #2 (due one week after distribution)
- Class 15
- Read lecture slides on Convolutional neural networks (CNNs) for visual perception

Read "Deep Learning for Computer Vision" by Chollet - Class 16
- Read lecture slides on Implementing CNNs in Python

Read "Deep Learning for Computer Vision" by Chollet - ***Distribute Homework #3 (due one week after distribution)
- Class 17
- Student presentation of papers
- Read "Using goal-driven deep learning models to understand sensory cortex" by Yamins and DiCarlo

Read "Deep neural networks: A new framework for modeling biological vision and brain information processing" by Kriegeskorte - Class 18
- Student presentation of papers
- Read "Capturing human categorization of natural images by combining deep networks and cognitive models" by Battleday, Peterson, and Griffiths

Read "Deep neural networks predict category typicality ratings for images" by Lake, Zaremba, Fergus, and Gureckis - Class 19
- Few-shot learning; Generative modeling
- Read lecture slides on Few-shot learning and generative models
- Class 20
- Read lecture slides on Python Implementation of VAEs
- Class 21
- Student presentation of papers
- Read "Face space representations in deep convolutional neural networks" by O'Toole, Castillo,
Parde, Hill, and Chellappa

Read "Unsupervised deep learning identities semantic disentanglement in single inferotemporal face patch neurons" by Higgins, Chang, Langston, Hassabis, Summerfield, Tsao, and Botvinick - Class 21
- Student presentation of papers
- Read "Face space representations in deep convolutional neural networks" by O'Toole, Castillo,
Parde, Hill, and Chellappa

Read "Unsupervised deep learning identities semantic disentanglement in single inferotemporal face patch neurons" by Higgins, Chang, Langston, Hassabis, Summerfield, Tsao, and Botvinick - Class 22
- Student presentation of papers
- Read "Face recognition accuracy of forensic examiners, superrecognizers, and face recognition
algorithms" by Phillips, Yates, Hu, Hahn, Noyes, et al.

Read "Computational insights into human perceptual expertise for familiar and unfamiliar face recognition" by Blauch, Behrmann, and Plaut - Class 23-24
- Preparation for student presentations of final projects
- Class 25-28
- Student presentations of final projects