Deep Learning
Deep Learning | News, how-tos, features, reviews, and videos
TensorFlow 2.10 shines on Keras, Decision Forests
Update to Google’s open source machine learning platform brings Keras improvements, performance enhancements, and TensorFlow Decision Forests 1.0.
TensorFlow, PyTorch, and JAX: Choosing a deep learning framework
Three widely used frameworks are leading the way in deep learning research and production today. One is celebrated for ease of use, one for features and maturity, and one for immense scalability. Which one should you use?
Microsoft previews text classification API for ML.NET
New text classification API for Microsoft’s open source machine learning framework streamlines model training by using your data to fine-tune an existing model.
What is PyTorch? Python machine learning on GPUs
PyTorch 1.10 is production ready, with a rich ecosystem of tools and libraries for deep learning, computer vision, natural language processing, and more. Here's how to get started with PyTorch.
What is neural architecture search? AutoML for deep learning
Neural architecture search promises to speed up the process of finding neural network architectures that will yield good models for a given dataset.
Review: Nvidia AI Enterprise shines on VMware
Nvidia’s VMware-optimized AI software stack offers a strong alternative to doing machine learning in the AWS, Azure, and Google clouds. Nvidia LaunchPad lets you try it out for free.
UNESCO launches global standard for AI ethics
Standard aims to provide AI with a strong ethical basis that will not only protect but also promote human rights and human dignity.
Explainable AI explained
Someday machine learning models may be more ‘glass box‘ than black box. Until then, explainability tools and techniques can help us understand how a black box model makes its decisions.
Review: Google Cloud Vertex AI irons out ML platform wrinkles
Vertex AI greatly improves the integration of Google Cloud’s AI/ML platform and AutoML services, combining a new unified API with very good modeling capabilities.
What is vector search? Better search through AI
Vector similarity search uses machine learning to translate the similarity of text, images, or audio into a vector space, making search faster, more accurate, and more scalable.
Machine learning is moving beyond the hype
Today, companies across every industry are deploying millions of machine learning models across multiple lines of business. Soon every enterprise will take part.
What is AI bias mitigation, and how can it improve AI fairness?
Algorithmic biases that lead to unfair or arbitrary outcomes take many forms. But we also have many strategies and techniques to combat them.
3 ways AI improves CRM
AI has the power to liberate organizations from CRM-related manual processes and improve customer engagement, sales insights, and social networking, for starters.
OpenAI debuts Python-based Triton for GPU-powered machine learning
Triton uses Python’s syntax to compile to GPU-native code, without the complexities of GPU programming.
Design for responsible AI with Microsoft’s HAX
Microsoft Research’s Human-AI eXperience toolkit makes us think about how we use AI in our code.
5 AI startups out to change the world
Deep learning is solving challenging problems in industries as diverse as retail, manufacturing, and agriculture. These companies are leading the way.
How the cloud and big compute are remaking HPC
High-performance computing projects require massive quantities of compute resources. Pairing simulation and specialized hardware with the cloud powers the breakthroughs of the future.
