DeepParticle: Learning Invariant Measure by Deep Neural Network Minimizing Wasserstein Distance
Explore DeepParticle: an integrated approach combining deep learning, optimal transport, and interacting particles to solve high-dimensional PDEs, demonstrated through Fisher-Kolmogorov-Petrovsky-Piskunov front speeds in incompressible flows.
Intrusive Model Order Reduction Using Neural Network Approximants
Explore innovative neural network-based techniques for efficient reduced-order modeling of complex parametric partial differential equations, focusing on intrusive and interpretable methodologies.
Multimodal Generative AI: Technology Overview and Business Implications
Explore multimodal generative AI's technology, business applications, and limitations. Gain insights into training, costs, and open-source systems like LLaVA for text, image, and audio processing.
Deploying Deep Learning Models for Inference at Production Scale
Optimize and deploy AI models at scale using NVIDIA TensorRT and Triton Inference Server. Learn production-ready techniques for efficient inference across various platforms and infrastructures.
Introduction to Neural Networks
Explore neural networks, their components, and architectures. Learn about RNNs, LSTMs, and CNNs with practical examples in Python for movie review and image classification tasks.
From Simplicity to Complexity: The Double Descent Effect in Modern Machine Learning
Explore the double descent effect in modern machine learning, transitioning from simplicity to complexity. Gain insights into this intriguing phenomenon and its implications.
Combinatorial Optimization Augmented Machine Learning for Contextual Multi-Stage Problems
Explore combinatorial optimization augmented machine learning for contextual multi-stage problems, focusing on industrial applications and dynamic stochastic optimization challenges.
The Mathematical Foundations of Deep Learning: From Rating Impossibility to Practical Existence Theorems
Explorez les fondements mathématiques de l'apprentissage profond, de l'impossibilité de notation aux théorèmes d'existence pratique. Découvrez les défis et les avancées dans ce domaine en pleine expansion.
Understanding the Visual World Through Object Intrinsics
Explore neuro-symbolic approaches to scene and object understanding, focusing on intrinsic structures and their role in visual data interpretation and generalization.
Prediction of Multi-Class Peptides by T-Cell Receptor Sequences with Deep Learning
Explore deep learning techniques for predicting multi-class peptides using T-cell receptor sequences, enhancing immune system understanding and potential disease treatments.
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Explore a novel fine-tuning method for Large Language Models that improves performance without additional human-annotated data, using self-play mechanisms and theoretical guarantees.
Deep AutoViML for TensorFlow Models and MLOps Workflows
Explore Deep AutoViML for building powerful TensorFlow models and MLOps workflows. Learn to fast prototype data pipelines and models using TF 2.4+ and Keras preprocessing layers.
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.
TinyEngine - Efficient Training and Inference on Microcontrollers - Lecture 17
Explore TinyEngine library for efficient neural network training and inference on microcontrollers. Learn techniques to optimize deep learning for resource-constrained devices.
Efficient Video Understanding and Generative Models - Lecture 19
Explore efficient video understanding and generative models, focusing on techniques for deploying neural networks on resource-constrained devices and optimizing deep learning applications.
Efficient Video Understanding and Generative Models - Lecture 19
Explore efficient video understanding and generative models, focusing on techniques for deploying neural networks on resource-constrained devices and optimizing deep learning applications.
EfficientML.ai: Quantization Part II - Lecture 6
Explore advanced quantization techniques for efficient machine learning, including Rooney quantization, scaling factors, and fine-tuning strategies.
Basics of Neural Networks - Lecture 2
Explore neural network fundamentals, including architecture, training, and optimization techniques for efficient machine learning model development.
Quantization for Efficient Machine Learning - Part II
Explore advanced quantization techniques for efficient machine learning, including post-training and quantization-aware training methods.
MCUNet: TinyML on Microcontrollers - Lecture 10
Explore MCUNet for TinyML on microcontrollers, covering efficient neural architecture design and deployment strategies for resource-constrained devices.