PirateNets - Physics-Informed Deep Learning with Residual Adaptive Networks
Explore PirateNets: a novel deep learning architecture for solving PDE-governed problems, offering improved stability and efficiency over traditional physics-informed neural networks.
AlphaFold and Beyond - How AI and Data Science are Revolutionizing Biology
Explore AI's impact on biology, focusing on AlphaFold's protein structure prediction and advancements in health data science and genomics with Professor Tim Hubbard.
Scaling AI Sustainably: An Uncharted Territory
Explore AI's environmental impact, efficiency optimization, and sustainable scaling strategies. Gain insights into the computing lifecycle and future research directions for responsible AI development.
Deep Learning Based Side Channel Attacks
Explore cutting-edge deep learning techniques for side channel attacks in cryptography, focusing on latest research and advancements in this critical security field.
The Geometry of the Deep Linear Network - Part 2
Explore the intricate geometry of deep linear networks, delving into advanced mathematical concepts and their applications in machine learning architectures.
The Platonic Representation Hypothesis
Explore the Platonic Representation Hypothesis with MIT's Phillip Isola, delving into philosophical concepts and their applications in modern computational theory.
Stable Diffusion 3 2B Medium Training with Kohya and SimpleTuner - Full Finetune and LoRA
Comprehensive guide on training Stable Diffusion 3 for art styles using kohya and SimpleTuner, covering setup, parameters, experiments, and result analysis for both full finetune and LoRA approaches.
Deep Learning with Noisy Labels
Explore techniques for training deep learning models with noisy labels, addressing challenges in data collection and annotation across various domains, including medical imaging.
Introduction to Binarized Neural Networks
Explore binarized neural networks: motivation, quantization benefits, core concepts, training methods, and recent developments in this cutting-edge AI field.
Learning with Logical Constraints: Methods and Applications
Explore multiple methods for learning with logical constraints, including LTN, SPL, NASR, and STLNet. Gain insights into cutting-edge AI techniques combining symbolic methods and deep learning.
Full Fine-tuning LLMs with Lower VRAM: Optimizers, GaLore, and Advanced Techniques
Explore advanced techniques for full fine-tuning LLMs with limited GPU resources, including optimizer tricks, Galore, and Adafactor. Enhance model performance and efficiency.
Text-to-Speech Fine-tuning Tutorial - StyleTTS2 Voice Cloning and Model Adaptation
Master text-to-speech fine-tuning techniques, from dataset preparation to model training. Explore voice cloning, StyleTTS2, and performance optimization for advanced speech synthesis projects.
Custom RAG Pipelines and LLM Fine-Tuning - A Gradient Tutorial
Explore custom RAG pipelines and LLM fine-tuning using Gradient. Learn to deploy fine-tuned models, mimic Yoda's speech style, and efficiently fine-tune 13B parameter open-source models for unique applications.
LoRA Fine-tuning Explained - Choosing Parameters and Optimizations
Explore LoRA fine-tuning techniques, from parameter selection to optimization strategies, enhancing your ability to customize language models effectively.
Multi-GPU Fine-tuning with DDP and FSDP
Master multi-GPU fine-tuning techniques using DDP and FSDP. Explore VRAM optimization, distributed training strategies, and practical implementation with code examples and demos.
Using Unity's Machine Learning Agents on Arm for Game Character Training
Explore Unity's ML-Agents for intelligent game characters on Arm devices. Train agents using reinforcement learning for single and multi-agent scenarios in games and apps.
Domain Adaptation on Wheels: Closing the Gap to the Open-world
Explore domain adaptation techniques for autonomous driving, from standard unsupervised setups to practical approaches addressing open-world challenges in semantic segmentation and scene understanding.
Cutting-Edge AI Innovations at VinAI
Explore cutting-edge AI innovations at VinAI, led by Dr. Hung Bui. Discover advancements in probabilistic models, deep learning, and human-machine understanding across various applications.
Implicit Deep Learning - Seminar Series
Explore implicit deep learning models, their state-space representation, training problems, and applications in parameter reduction, feature elimination, and mathematical reasoning tasks.
Model-Constrained Deep Learning Approaches for Scientific Machine Learning
Explore model-aware machine learning methods combining scientific computing and data-driven models. Learn about ROM-ML and Autoencoder-based Inversion approaches for PDE-constrained inverse problems.
Mean Field Limit in Neural Network Learning
Explore the mean field limit in neural network learning, examining optimization dynamics, convergence to global optima, and data representation in autoencoders. Gain insights from physics analogies.