Curiosity and Reward: Neuroscience to AI

Related lectures (29)

Page 2 of 3

Introduces key concepts in probability and random variables, covering statistics, distributions, and covariance.

Introduces systems neuroscience, focusing on neural circuits, memory systems, and course logistics.

Covers key concepts in reinforcement learning, neural networks, clustering, and unsupervised learning, emphasizing their applications and challenges.

Explores the balance between exploration and exploitation in multi-arm bandit algorithms.

Explores independence and conditional probability in probability and statistics, with examples illustrating the concepts and practical applications.

Covers state space models and the expressivity of transformers in sequence copying tasks.

Covers the Bayes discriminant rule for allocating individuals to populations based on measurements and prior probabilities.

Delves into the continual learning of representational models after deployment, highlighting the limitations of current artificial neural networks.

Explores the gap between AI and human intelligence through neuroscience-inspired models and algorithms.

Covers Simpson's paradox, probability distributions, and real-life examples in probability and statistics.