Simons Institute Courses

Characterizing the Impact of Noise on Neural Computation

Exploring noise in biological and artificial neural networks, its impact on computations, and new methods for analyzing stochastic network representations and trial-to-trial variability.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Seeing Faces in Things: A Model and Dataset for Pareidolia

Explore face pareidolia through computer vision, examining human vs. machine detection abilities and proposing a statistical model for general object pareidolia in images.

• YouTube
• 51 minutes
• On-Demand
• Free Video

Neural Computations for Geometric Reasoning

Explore neural computations enabling animals to represent and process geometric structures in 3D environments, focusing on robust, low-power circuits for survival and navigation.

• YouTube
• 46 minutes
• On-Demand
• Free Video

Audio-Visual Self-Supervised Learning: Insights from Infant Development

Explore how neural networks learn audio-visual representations from video streams, mimicking infant learning through synchronization of sight and sound.

• YouTube
• 48 minutes
• On-Demand
• Free Video

Robust Equation Discovery and Sparse Sensing with Guarantees

Explore statistical mechanics for robust sparse equation discovery and optimal sensor placement, with applications in nuclear digital twins and high-dimensional field reconstruction.

• YouTube
• 1 hour
• On-Demand
• Free Video

Error Embraced - Making Trustworthy Scientific Decisions with Imperfect Predictions

Explore prediction-powered inference for valid statistical analysis using machine learning predictions, with applications in proteomics, genomics, and astronomy. Learn about reliable ML-guided decisions in biological sequence design.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Machine Learning Models of Differential Gene Expression

Explore deep learning models for predicting regulatory functions from genomic DNA, uncovering mechanisms behind genetic variation's impact on cellular function and gene expression.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Data is as Data Does - The Influence of Computation on Inference

Exploring the impact of computational approximations on probabilistic models in machine learning, with focus on Gaussian Process approximations and their applications in neurobiology.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

Machine Learning-Based Protein Engineering - Insights and Approaches

Explore ML-based protein engineering insights, discussing cutting-edge techniques and potential applications in biotechnology and drug discovery.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Symmetries in Machine Learning for Materials Science

Exploring machine learning techniques incorporating crystallographic symmetries for materials science, enhancing property prediction and discovery of new materials and meta-materials.

• YouTube
• 1 hour
• On-Demand
• Free Video

Open Challenges in AI for Molecular Design: Representation, Experimental Alignment, and Oracle Reliability

Explore AI challenges in molecular design: representation, experimental alignment, and oracle reliance. Learn about new workflows and approaches to address real-world complexities in molecular discovery.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Illuminating Protein Space with Generative Models

Explore generative modeling for protein design, focusing on building learning systems that can generalize, scale, and create fit-for-purpose protein complexes on demand.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Deep Learning and Numerical Methods Intersections for Improving Molecular and Fluid Dynamics

Explore intersections of deep learning and numerical methods to enhance molecular and fluid dynamics simulations, improving accuracy and efficiency in scientific computations.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Large ML Potentials for Chemistry - Generalization, Inductive Biases, and Error Cancellation

Explore machine learning potentials in chemistry, focusing on generalization, inductive biases, and error cancellation techniques for improved accuracy and efficiency.

• YouTube
• 1 hour 1 minute
• On-Demand
• Free Video

Machine Learning Gradients in Molecular Simulations

Explore ML gradients in molecular simulations, including surrogate functions, active learning, and differentiable programming for enhanced scientific modeling and optimization.

• YouTube
• 57 minutes
• On-Demand
• Free Video