Energy-Based Approaches to Representation Learning - Yann LeCun
Explore energy-based approaches to representation learning with Yann LeCun, covering self-supervised learning, video prediction, and sparse modeling in high-dimensional spaces.
Are All Features Created Equal? - Aleksander Madry
Explore machine learning's success, deep learning's appeal, and adversarial perturbations. Examine robust features, human vs. ML perspectives, and implications for data efficiency and image synthesis.
Overcoming the Curse of Dimensionality and Mode Collapse - Ke Li
Explore techniques to overcome dimensionality challenges and mode collapse in deep learning, focusing on GANs, maximum likelihood estimation, and efficient algorithms for high-dimensional spaces.
PAC-Bayesian Approaches to Understanding Generalization in Deep Learning - Gintare Dziugaite
Explore PAC-Bayesian approaches for understanding generalization in deep learning, covering risk bounds, optimal priors, and data-dependent techniques for neural networks.
Is Optimization the Right Language to Understand Deep Learning? - Sanjeev Arora
Explore deep learning optimization, generalization, and neural tangent kernels with Sanjeev Arora. Gain insights into training wide networks and matrix completion techniques.
Tightening Information-Theoretic Generalization Bounds with Data-Dependent Estimates with an Application to SGLD - Daniel Roy
Explore information-theoretic generalization bounds and their application to stochastic gradient Langevin dynamics, focusing on tightening bounds with data-dependent estimates.
Fixing GAN Optimization Through Competitive Gradient Descent - Anima Anandkumar
Explore competitive gradient descent for optimizing GANs, covering strategic equilibria, applications in ML, and numerical results. Gain insights into modeling competing agents and solving GANs.
Emergent Linguistic Structure in Deep Contextual Neural Word Representations - Chris Manning
Explore emergent linguistic structures in deep neural word representations with Stanford's Chris Manning, examining language models, attention mechanisms, and vector space analysis.
Entanglement Wedge Reconstruction and the Information Paradox - Geoff Penington
Explore quantum information in black holes, entanglement wedge reconstruction, and the resolution of the information paradox through advanced theoretical physics concepts.
Scrapbooking Techniques - How to Create Realistic Effects by Adding Textures to Photos
Learn to enhance photos with realistic textures using overlays, blending modes, and adjustment layers. Master techniques for adding water droplets, bokeh effects, and manipulating light for stunning scrapbook designs.
Generalization vs. Specialization as a Graphic Designer With Chris Do
Explore the debate between generalization and specialization in graphic design with Emmy-winning designer Chris Do, gaining insights on positioning, expertise, and career strategies.
Proof and Circuit Complexity - Robert Robere
Explore proof and circuit complexity with Robert Robere, delving into Boolean circuits, monotone circuits, slice functions, and the Click function to understand computational limitations.
Circadian Rhythms: Past, Present and Future - Michael Rosbash
Explore the fascinating world of circadian rhythms, from their evolutionary origins to their impact on modern health issues like metabolism and sleep disorders.
The General Case? - Amie Wilkinson
Explore ergodicity, Boltzmann's ideas, and recent developments in dynamical systems with mathematician Amie Wilkinson in this engaging seminar on the concept of "the general case".
A Brief Tour of Proof Complexity - Lower Bounds and Open Problems - Toniann Pitassi
Explore proof complexity, lower bounds, and open problems in computer science and discrete mathematics with insights on proof systems and their limitations.
Successes and Challenges in Neural Models for Speech and Language - Michael Collins
Explore neural models' impact on speech and language processing, examining successes, challenges, and key architectures in parsing, word embeddings, and transformers.
Reproducible, Reusable, and Robust Reinforcement Learning - Joelle Pineau
Explore reproducibility, reusability, and robustness in reinforcement learning. Delve into policy gradient methods, hyperparameter interplay, fair comparisons, and real-world applications of RL algorithms.
The Epistemology of Deep Learning - Yann LeCun
Explore deep learning's scientific foundations with Yann LeCun, examining its biological inspirations, historical development, and theoretical underpinnings in pattern recognition and neural networks.
Troubling Trends in ML Scholarship - Zachary Lipton
Exploration of concerning trends in machine learning research, examining the balance between empirical and theoretical approaches, and discussing potential solutions for improving scientific rigor.
Brief Introduction to Deep Learning and the "Alchemy" Controversy - Sanjeev Arora
Explore deep learning's scientific foundations and the "Alchemy" debate, examining optimization, overfitting, and the interpreter problem in neural networks.
A Toy Model of the Information Paradox in Empty Space - Suvrat Raju
Explore the information paradox in empty space through a toy model, examining quantum correlations, Bell inequalities, and their implications for gravity and spacetime structure.