Simons Institute Courses

Neural Mechanisms of Vision

Explore the intricate workings of visual perception, delving into neural processes and computational models that shape our understanding of how the brain interprets visual information.

• YouTube
• 1 hour 34 minutes
• Self-Paced
• Free Video

Computation in Networks of Neurons in the Brain I

Explore neural network computation in the brain, focusing on advanced concepts and recent research findings in computational neuroscience.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Mapping Neural Connections and Their Development II

Explore neural connectivity mapping and developmental processes in the brain, focusing on advanced techniques and recent findings in neuroscience research.

• YouTube
• 1 hour 12 minutes
• Self-Paced
• Free Video

Mapping Neural Connections and Their Development I

Explore neural connectivity mapping and developmental processes in the brain, focusing on cutting-edge techniques and insights from Harvard research.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

The Power and Limitations of Kernel Learning

Explore kernel learning's potential and limitations in modern machine learning, including practical implementations, comparisons with state-of-the-art methods, and insights into overfitting and acceleration.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Learning One-Hidden-Layer Neural Networks with Landscape Design

Explore optimization techniques for one-hidden-layer neural networks, focusing on landscape design and new objective functions to overcome traditional training challenges.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Fast Spectral Algorithms from Sum-of-Squares Analyses

Explore efficient spectral algorithms derived from sum-of-squares analyses, focusing on hierarchies, extended formulations, and matrix-analytic techniques in computational complexity.

• YouTube
• 39 minutes
• Self-Paced
• Free Video

LP, SOCP, and Optimization-Free Approaches to Polynomial Optimization

Explore advanced techniques in polynomial optimization, including LP, SOCP, and optimization-free methods, with a focus on hierarchies and matrix-analytic approaches.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

A Nearly-Linear Time Algorithm for Submodular Maximization with a Knapsack Constraint

Explore efficient algorithms for submodular maximization with knapsack constraints, focusing on nearly-linear time solutions and their applications in discrete optimization.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Computationally Tractable and Near Optimal Design of Experiments

Explore near-optimal experimental design strategies that balance computational efficiency with statistical power, enhancing machine learning outcomes in complex systems.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

Computational Challenges and the Future of ML Panel

Experts discuss computational challenges in machine learning, exploring open problems and future directions in the field with insights from leading researchers.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Embedding as a Tool for Algorithm Design

Explore embedding algorithms for structured data prediction, combinatorial optimization, and dynamic network processes. Learn innovative approaches to algorithm design using latent variable models and mean field techniques.

• YouTube
• 1 hour 8 minutes
• Self-Paced
• Free Video

A Cost Function for Similarity-Based Hierarchical Clustering

Explore a novel cost function for similarity-based hierarchical clustering, examining its theoretical properties and practical implications for machine learning algorithms.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Unbiased Estimation of the Spectral Properties of Large Implicit Matrices

Explore techniques for estimating spectral properties of large implicit matrices, focusing on unbiased methods and their applications in machine learning and computational challenges.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

Composing Graphical Models with Neural Networks for Structured Representations and Fast Inference

Explore structured representations and fast inference by combining graphical models with neural networks, enhancing machine learning capabilities.

• YouTube
• 42 minutes
• Self-Paced
• Free Video