Notes with code

Notes on Probabilistic Models of Cognition

• Chapter 3: Conditioning
• Chapter 4: Causal & Statistical Dependence
• Chapter 5: Conditional Dependence
• Chapter 6: Bayesian Data Analysis
• Chapter 7: Algorithms for Inference
• Chapter 9: Learning as Conditional Inference
• Chapter 10: Learning with a Language of Thought
• Chapter 11: Hierarchical Models
• Chapter 12: Occam’s Razor
• Chapter 13: Learning Deep Continuous Functions
• Chapter 14: Mixture Models
• Chapter 15: Social Cognition

Notes on Self-supervised Learning

• Contrastive Predictive Coding
• MoCo
• Contrastive Multiview Coding
• Deep InfoMax
• SimCLR
• Invariant Information Clustering
• On Mutual Information Maximization for Representation Learning

Notes on Visual Transformers

• An Image is worth 16x16 words
• DEIT: Data Efficient Image Transformers
• DiNo: self-DIstillation with NO labels
• BeIT: Bert Encoding representations for Image Transformers

Notes along the theme of transformers are NOT all what you need?

• MLP-Mixer
• Patches are all you need?
• Metaformer is actually what you need for vision