Foundations for Feature Learning via Gradient Descent
Explore the theoretical foundations of feature learning in modern machine learning models, focusing on gradient descent's role in extracting useful features and representations from data.
History of Language Models: Evolution, Frameworks, and Deployment
Explore language models' evolution from early systems to neural networks, transformers, and large-scale pretraining. Gain insights on key frameworks and real-world deployment strategies.
How Well Do Sparse Models Transfer? - Exploring Transfer Performance in Computer Vision and NLP
Explore sparse models' transfer performance and efficiency gains in image and language tasks, outperforming dense models even at high sparsities.
Comparing Representations Learned by Neural Networks - Deconfounded Similarity Measures
Explore improved methods for comparing neural network representations, addressing data structure confounding and enhancing functional similarity identification in transfer learning and out-of-distribution scenarios.
Toward Building a Cost-Effective and Robust Machine Learning System
Explore cost-effective ML system development through active learning, continual learning, and transfer learning. Learn efficient model selection techniques for optimal source model transfer to target tasks.
Creating a Horse Race Detection Model using Deep Learning
Learn to create a horse race detection model using deep learning without a pre-existing dataset. Extract frames, automate annotations, train YOLOv8, and apply the model to videos for real-time object detection.
Building Your First GenAI App Using Databricks, MosaicML and MLRun
Learn to implement, scale, and manage GenAI applications using Databricks, MosaicAI, and MLRun. Explore MLOps best practices, CI/CD automation, and GPU optimization for enterprise-level AI deployment.
Leveraging Knowledge to Design Machine Learning Despite Limited Data
Explorez les méthodes d'apprentissage automatique pour les petits ensembles de données industrielles, en utilisant le transfert de connaissances et les modèles hybrides pour des outils d'aide à la décision efficaces.
Efficient Model Development in the Era of Large Language Models
Delve into advanced techniques for efficient LLM development, covering optimal dataset mixing strategies and novel model merging approaches for enhanced AI capabilities and performance.
Getting Started with Generative Text and Fine-Tuning LLMs in Hugging Face
Dive into practical LLM implementation using Hugging Face's transformers library, from basic text generation to efficient model fine-tuning techniques for customized applications.
Vision Transformer - Lecture 16
Dive into Vision Transformers architecture and implementation, exploring their role in computer vision tasks through expert insights and practical applications in machine learning.
LLM Post-Training - Lecture 14
Dive into advanced LLM post-training techniques and methodologies with Prof. Song Han, exploring efficient machine learning strategies for optimizing large language models.
The Unreasonable Effectiveness of Mathematics in Large Scale Deep Learning - From Theory to Practice
Explore the mathematical foundations of large-scale deep learning, focusing on infinite-width neural networks and their practical applications in tuning enormous models like GPT-3.
ML-driven Models for Material Microstructure and Mechanical Behavior - DDPS
Explore ML-driven approaches for generating microstructures and accelerating material behavior analysis. Learn transfer learning techniques and rapid assessment methods for materials design optimization.
Data-Driven Multi-Scale Simulations for Materials-by-Design of Energetic Materials
Explore multi-scale modeling of energetic materials using machine learning for scale bridging. Learn about structure-property-performance relationships and optimization strategies for materials design.
Building AI Applications with Transformers
Learn to leverage transformers for AI applications like auto-completion, semantic search, and document AI using open-source tools and models. Explore embeddings, Generative AI, and emerging trends in multimodal and large language models.
10X Faster Machine Learning: From R&D to Production
Supercharge ML experimentation with PyTorch Lightning and DVC, and streamline production using Kubeflow. Learn to overcome challenges in complex ML model development and deployment.
On-Device Training and Transfer Learning - Lecture 15
Explore on-device training and transfer learning techniques, focusing on memory bottlenecks, efficient algorithms like TinyTL, and system support for optimized on-device training.
On-Device Training and Transfer Learning - Lecture 15
Explore on-device training and transfer learning techniques, focusing on memory bottlenecks, efficient algorithms like TinyTL, and system support for optimized on-device training.
Vision Transformer - Lecture 14
Explore Vision Transformers in deep learning, covering architecture, training, and applications. Gain insights into this powerful model for computer vision tasks.
Vision Transformer - Lecture 14
Explore Vision Transformers in deep learning, covering architecture, training, and applications. Gain insights into this powerful model for computer vision tasks.