Deep Learning
Deep Learning | News, how-tos, features, reviews, and videos
The engines of AI: Machine learning algorithms explained
Machine learning uses algorithms to turn a data set into a model that can identify patterns or make predictions from new data. Which algorithm works best depends on the problem.
Build accelerated AI apps for NPUs with Olive
Microsoft’s open-source, hardware-aware optimization tool for ONNX models is an essential part of its AI application development tool chain.
14 popular AI algorithms and their uses
Large language models have captured the news cycle, but there are many other kinds of machine learning and deep learning with many different use cases.
7 speed bumps on the road to AI
Artificial intelligence is rife with practical and ethical dilemmas, and now they're coming home to roost. Here are seven unavoidable questions about AI.
10 reasons to worry about generative AI
After decades of speculation, real-world artificial intelligence has finally hit a tipping point. Now that we know what AI models like ChatGPT and DALL-E can do, should we be worried?
![Aerial view of circular stairs [movement/progress/descent/exit]](https://images.idgesg.net/images/article/2019/02/stairs_staircase_movement_progress_descent_by_dan_freeman_cc0_via_unsplash_2400x1600-100788539-small.3x2.jpg?auto=webp&quality=85,70)
Gradient descent in Java
Find out why backpropagation and gradient descent are key to prediction in machine learning, then get started with training a simple neural network using gradient descent and Java code.
How to build a neural network in Java
The best way to understand neural networks is to build one for yourself. Let's get started with creating and training a neural network in Java.
Styles of machine learning: Intro to neural networks
Modeled on the human brain, neural networks are one of the most common styles of machine learning. Get started with the basic design and concepts of artificial neural networks.
10 databases supporting in-database machine learning
While approaches and capabilities differ, all of these databases allow you to build machine learning models right where your data resides.
How to choose a cloud machine learning platform
12 capabilities every cloud machine learning platform should provide to support the complete machine learning lifecycle—and which cloud machine learning platforms provide them.
What is CUDA? Parallel programming for GPUs
NVIDIA’s CUDA is a general purpose parallel computing platform and programming model that accelerates deep learning and other compute-intensive apps by taking advantage of the parallel processing power of GPUs.
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.
