Noether Networks - Meta-Learning Useful Conserved Quantities
Explore Noether Networks: a novel approach to meta-learning conserved quantities in sequential prediction problems, inspired by Noether's theorem and aimed at discovering useful symmetries and inductive biases.
Bringing Choice, Automation and Performance to ML Deployment with Apache TVM and the OctoML Platform
Explore Apache TVM for ML deployment across diverse hardware, offering performance optimization and portability. Learn about OctoML's Octomizer for continuous model optimization and benchmarking.
Debugging Neural Nets for NLP
Comprehensive guide to diagnosing and resolving issues in neural networks for NLP, covering training, decoding, overfitting, and optimization techniques.
Neural Nets for NLP - Debugging Neural Nets
Learn techniques for identifying and resolving issues in neural networks for NLP, covering training and test-time problems, optimization strategies, and performance analysis.
LORA for Stable Diffusion - Dreambooth Extension - 6GB VRAM
Learn to train custom AI models using LORA Dreambooth for Stable Diffusion, even with limited 6GB VRAM. Discover faster, smaller, and improved techniques for personalized image generation.
XGBoost and Data Leakage in Machine Learning - Day 14 of 30 Days of ML
Explore XGBoost and data leakage in machine learning. Learn to build optimized models, prevent leakage issues, and enhance your ML skills with practical tutorials and exercises.
Improving the Life of Data Scientists - Automating ML Lifecycle through MLflow
Explore Flock, an end-to-end platform leveraging MLflow to automate and simplify enterprise-grade machine learning, enhancing data scientist productivity and addressing regulatory challenges in ML adoption.
Model Optimization - Series Conclusion - Introduction to Text Analytics with R
Optimize text analytics models, explore sensitivity/specificity tradeoffs, and discover resources for further study in R. Learn feature engineering and algorithm selection for improved effectiveness.
Movement Pruning - Adaptive Sparsity by Fine-Tuning
Explore Movement Pruning, an adaptive sparsity technique for fine-tuning deep neural networks. Learn its advantages over Magnitude Pruning in transfer learning scenarios and its impact on model efficiency.
Deconstructing Lottery Tickets - Zeros, Signs, and the Supermask
Explores the Lottery Ticket Hypothesis, analyzing key components of sparse networks and uncovering insights on weight initialization, sign importance, and the concept of Supermasks in neural network training.
Turing-NLG, DeepSpeed and the ZeRO Optimizer
Explore Microsoft's 17-billion parameter language model, ZeRO optimizer, and DeepSpeed, enabling efficient model and data parallelism for state-of-the-art natural language processing breakthroughs.
RoBERTa - A Robustly Optimized BERT Pretraining Approach
Explore how RoBERTa improves BERT's performance through optimized training, challenging recent model enhancements and highlighting the impact of hyperparameter choices in language model pretraining.
Convolutional Neural Networks with TensorFlow 2022
Comprehensive live-coding tutorial on Convolutional Neural Networks using TensorFlow, covering data preparation, model architecture, optimization techniques, and practical applications in image recognition and object detection.
Audio Processing in Keras with Kapre
Learn to process audio in Keras using Kapre, exploring its advantages, features, and implementation. Discover how to embed audio transformations within deep learning models for optimized GPU-based calculations and easier deployment.
Open AI's Whisper Is Amazing
Explore OpenAI's Whisper, a powerful speech recognition model capable of transcribing and translating 97 languages, with insights on its implementation, training, and performance.
Leaner and Greener AI with Quantization in PyTorch - Suraj Subramanian
Discover how quantization in PyTorch can make AI models lighter, faster, and more power-efficient without compromising accuracy. Learn techniques and workflows from an ML expert at Meta AI.
Tuning Machine Learning Models - Scaling, Workflows, and Architecture
Automating and scaling ML model tuning using Hyperopt and Apache Spark. Best practices for workflows, architecture, and optimization in hyperparameter tuning for improved performance and accuracy.
Scaling Up AI Research to Production with PyTorch and MLFlow
Explore PyTorch's latest advancements in AI research and production, including distributed training, model optimization, and deployment using MLFlow, with insights on scaling and efficiency.
1 kB and Not a Bit More - The Ideal Weight for a TinyML Model
Explore automated creation of ultra-compact ML models for tiny smart devices, enabling efficient embedding in memory-constrained hardware without data science expertise.
NVIDIA Tools for Training and Deploying Intelligent Vision Applications at the Edge
Discover tools for training, building, and deploying intelligent vision applications at the edge using NVIDIA's suite for video analytics pipelines and IoT devices.
Inference and Quantization for AI - Session 3
Explore quantized inference, TensorRT 5, and TensorFlow integration for AI model optimization. Learn about NVIDIA's inference server and techniques to improve model efficiency and performance.