A View in Old and New Machine Learning
Explore old and new machine learning approaches, comparing hierarchical probabilistic models with deep neural networks and examining their unique capabilities and potential combinations.
Stochastic Gradient Descent Methods with Biased Estimators
Explore recent advancements in stochastic gradient descent methods, focusing on biased estimators for large-scale optimization and minimax problems in machine learning applications.
Benign Overfitting in Linear Regression and Deep Learning
Explore benign overfitting in deep learning with Peter Bartlett. Uncover insights on linear regression, effective rank, and overparameterization in neural networks for optimal prediction accuracy.
3D Scenes - Understanding and Rendering
Explore 3D scene understanding and rendering techniques, from data acquisition to neural networks for point cloud classification and semantic segmentation, with insights on future research directions.
3D Face Modeling from a Single RGB Image
Explore techniques for 3D face reconstruction from single images, from coarse to fine-grain methods, addressing challenges in diverse real-world conditions.
Building Deep Retrieval Models in Practical Applications
Explore deep retrieval models for efficient web-scale data search, balancing accuracy and computational cost. Learn techniques for training robust models with limited labeled data.
Collision Course: Artificial Intelligence Meets Fundamental Interactions
Explore the synergy between machine learning and fundamental physics, focusing on particle physics at the Large Hadron Collider and its potential to advance AI research.
MRI Brain Scan Classification Using FastSurfer, XGBoost and 3D CNNs
Master medical image classification techniques using FastSurfer pipeline, XGBoost, and 3D CNNs for MRI brain scan analysis. Learn preprocessing steps and implement neural networks in PyTorch for advanced medical data analysis.
Efficiency in the Age of Large Scale Models - Designing and Optimizing Deep Learning Systems
Explore the challenges and solutions of large-scale AI models, from theoretical foundations to practical efficiency improvements, with insights on reducing computational costs while maintaining performance in modern machine learning.
Empirical Challenges to Theories of Deep Learning
Explore empirical challenges in deep learning theory, examining network representations, non-monotonic training patterns, and complex learning processes through cutting-edge research findings and real-world examples.
Benefits of Deep and Narrow Neural Networks for Approximation and Memorization
Explore groundbreaking research on neural networks' architecture, revealing why depth trumps width in function approximation and how deep, narrow networks can efficiently memorize data using minimal parameters.
ML and the IoT - Living on the Edge
Explore Edge ML in IoT: faster insights, enhanced security, and predictive action. Learn practical ways to leverage ML on embedded systems and microcontrollers for IoT applications.
Breaking Black-Box AI
Explore failure cases of popular AI algorithms through live demos, from linear regression to deep learning. Learn to identify and address silent failures in black-box AI systems.
Reinforcement Learning - Pac-Man
Explore reinforcement learning through building a Pac-Man-beating agent. Gain insights into Q-learning, deep Q-learning with neural networks, and practical implementation using libraries like Keras.
Understanding ChatGPT: From Machine Learning to Language Models
Explore machine learning, neural networks, and GPT technology. Gain insights into the evolution and inner workings of ChatGPT, from basic concepts to advanced applications.
EfficientML.ai Lecture - Introduction to Efficient Machine Learning
Explore cutting-edge techniques for optimizing machine learning models, focusing on efficiency and performance in AI applications.
Pruning and Sparsity in Machine Learning - Part I (EfficientML.ai Lecture 3)
Explore pruning and sparsity techniques for efficient machine learning, focusing on reducing model size and computational requirements while maintaining performance.
Basics of Neural Networks - EfficientML.ai Lecture 2
Explore neural network fundamentals, including architecture, training, and optimization techniques, in this comprehensive MIT lecture on efficient machine learning.
EfficientML.ai: Introduction to Efficient Machine Learning - Lecture 1
Explore efficient machine learning techniques and their applications in this comprehensive introduction to EfficientML.ai from MIT's Prof. Song Han.
EfficientML.ai: Introduction to Efficient Machine Learning - Lecture 1
Explore efficient machine learning techniques and their applications in this introductory lecture from MIT's EfficientML course, led by Prof. Song Han.
Machine Learning Fundamentals - Lecture 22
Dive into advanced data science concepts through comprehensive coverage of machine learning principles, algorithms, and practical applications in this graduate-level lecture from University of Utah.