Speech Recognition on Low Power Devices
Explore multilingual speech recognition on low-power devices, covering model optimization techniques, neural network compression, and practical demonstrations for efficient implementation.
Conversational AI with Transformer Models - Building Blocks and Optimization Techniques
Explore building conversational AI agents using transformer models, covering advantages over RNN/LSTM, knowledge distillation, and model compression techniques for efficient production deployment.
Automated Background Removal Using PyTorch - Wehkamp's Image Processing Pipeline
Discover an automated pipeline for efficient background removal in product images using PyTorch and machine learning, enhancing visual experiences for e-commerce customers.
Building AutoML Pipelines with Argo Workflows and Katib
Explore AutoML pipelines using Argo Workflows and Katib for efficient model selection and hyperparameter tuning in Kubernetes environments, enhancing MLOps processes.
PyTorch: A Foundation for Open Source AI/ML - Live Webinar
Explore PyTorch's evolution, usage, and future with its creator. Learn about the new PyTorch Foundation and discover opportunities in open-source AI/ML development.
AMD Hardware, Software and Libraries for Developing AI/ML Applications Using PyTorch
Explore AMD's ecosystem for developing AI/ML applications with PyTorch, including hardware, software, and libraries optimized for high-performance machine learning workflows.
Generative AI and Stable Diffusion - Lightning Talks
Explore cutting-edge AI topics: generative models, Stable Diffusion, and Intel's optimizations for PyTorch 2.0 in these concise, informative lightning talks.
PyTorch 2.0 - Unlocking the Power of Deep Learning with the Torch Compile API
Explore PyTorch 2.0's key features, including backwards compatibility and 43% faster model training. Learn about the torch compile API and its impact on streamlining deep learning development.
Machine Learning in Fastly's Compute@Edge
Explore WebAssembly modules for efficient ML model execution in Fastly's Compute@Edge, covering wasi-nn extensions, host API revisions, and KServe protocol integration for enhanced performance.
How Amazon Search Leverages PyTorch to Build and Deploy LLMs in Production
Explore Amazon Search's innovative use of PyTorch and its ecosystem for building and deploying large language models in production environments.
How PyTorch Became the Foundation of the AI Revolution
Explore the rise of PyTorch as a pivotal framework in AI development, its impact on the industry, and its role in shaping the future of artificial intelligence.
Training Foundation Model Workloads on Kubernetes at Scale with MCAD
Explore how IBM's Vela supercomputer uses MCAD to queue custom resources for large-scale AI training on Kubernetes, enabling flexible frameworks and fault tolerance across hundreds of GPUs.
PyTorch Foundation - One Year of Open Governance and Future Directions
Explore PyTorch Foundation's first year: growth, achievements, and future plans. Learn about community expansion, key releases, and the foundation's role in advancing open-source AI technologies.
Build Your First PyTorch Model - Image Classification Tutorial
Learn to build an image-classifying PyTorch model for playing cards in this hands-on tutorial. Covers datasets, model creation, training, and result analysis.
CNN Confusion Matrix with PyTorch - Neural Network Programming
Learn to build, plot, and interpret a confusion matrix using PyTorch for neural network evaluation, including techniques for disabling gradient tracking and analyzing model performance across different classes.
CNN Training Loop Explained - Neural Network Code Project
Learn to build a convolutional neural network training loop using Python and PyTorch. Gain practical skills in implementing deep learning algorithms for image processing tasks.
CNN Weights - Learnable Parameters in PyTorch Neural Networks
Explore PyTorch's inner workings, including OOP concepts, convolutional and linear layer weight tensors, and matrix multiplication for deep learning in neural networks.
Build PyTorch CNN - Object-Oriented Neural Networks
Learn to build a convolutional neural network using PyTorch for computer vision and AI applications. Gain hands-on experience in implementing object-oriented neural network architectures.
How to Eliminate I/O Bottleneck and Continuously Feed GPU While Training in the Cloud
Optimize I/O for GPU-intensive machine learning training in the cloud. Learn a new architecture to maintain data throughput and implement it in Kubernetes for PyTorch workloads.
Fireside Chat: PyTorch Foundation - Evolution, Usage, and Future
Insightful discussion on PyTorch's open-source journey, its widespread adoption, and future direction under the PyTorch Foundation. Explores governance, contributions, and upcoming developments.
Angel 3.0 - A Full Stack Machine Learning Platform
Explore Angel 3.0, a comprehensive machine learning platform featuring auto feature engineering, hyperparameter tuning, model serving, and PyTorch integration for enhanced graph embedding and GNN algorithms.