Note: This list is not yet complete.

Language and Concept Acquisition

This is a list of papers that might be useful if you're trying to create an artificial agent that can learn a language or a concept in a manner identical to human learning. Before you start working with RNNs, LSTMs and other complicated deep-learning architecture, I think it is important that you understand the basics of how humans learn a concept or a language and also some basic information about causal inference. This would mean reading a few papers written by Psychologists and Cognitive Scientists.

I have divided this list into a number of sections.

Psychology, Cognitive Science and Linguistics

• A history of Acquisition and Bickerton's Bioprogram
• A Comparison of Inference Learning and Classification Learning
• Correlation versus prediction in children’s word learning

Probabilisitic models and Bayesian Inference

• Probabilistic models of cognition
• Generality, Similarity and Bayesian Inference
• Word Learning as Bayesian Inference
• Building Machines That Learn and Think Like People
• Human-level concept learning through probabilistic program induction
• Introduction to causal inference

Complex models

• A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment
• Deep Reinforcement Learning: An overview
• Reinforcement Learning with Unsupervised Auxillary Tasks
• Grounded Language Learning in a Simulated 3D World

Other useful Machine Learning literature

• Correlation based Feature Selection
• Feature Selection for High-Dimensional Data