neuroscience-ai-reading-course

Neuroscience & AI Reading Course

Notes for the Neuroscience & AI Reading Course (SEM-I 2020-21) at BITS Pilani Goa Campus

The notes are available here

NLP & Syntax

  1. LSTMs & BERT

Syntactic Structures in Language models

  1. Assessing BERT’s syntactic abilities - Goldberg
  2. What does BERT learn about the structure of the language - Sagot
  3. Transferring pre trained Language Models

Semantics of Mental Lexicon Development

  1. Lexical Semantic Change

NCC-MARL

  1. NCC-MARL

Brain Embeddings

  1. Brain Data Embeddings
  2. Comparing Word Embeddings for Predicting Neural Activity

Imagined Speech Classification

  1. Envisioned speech recognition using EEG sensors
  2. Toward EEG Sensing of Imagined Speech
  3. EEG Sensing of Imagined Speech

Inductive biases in Deep Reinforcement Learning

  1. On inductive biases in Deep Reinforcement Learning
  2. Deep Reinforcement Learning with Relational Inductive biases
  3. Relational Inductive biases for physical construction in humans and machines
  4. Putting bandits into context - How functional learning supports decision making

social intrinsic motivation and self play MARL

  1. AlphaStar II multi agent Reinforcement Learning
  2. Hide and Seek
  3. Intrinsic Social Motivation

Grounded Language Learning

  1. Visually Grounded Neural Syntax Acquisition
  2. GLL_Notes

Deep Cognitive Models of Language Acquisition

  1. Multi SimLex: A large scale evaluation of multilingual and cross lingual lexical semantic similarity
  2. Neural Language Models for the Multilingual, Transcultural, and Multimodal Semantic Web

Inductive Bias in Meta-Reinforcement Learning

  1. MAML
  2. MAML as Hierarchical Bayes
  3. On inductive biases in DRL

Modeling Selective-Attention with Neural Networks

  1. Introduction to Selective Attention and Cognitive Neuroscience

Neural Correlates of Discourse and Analyzing Aphasia

  1. AphasiaBank: Methods for Studying Discourse
  2. Unsupervised corpus-wide claim detection