Get Started with Deep Learning
1. Study the Basics
Read the Deep Learning in a Nutshell blog post.
Study the NVIDIA® online deep learning course.
Read the Hacker's guide to Neural Networks, by Andrej Karpathy.
2. Select the Software That’s Right for You
Data Scientists: Download NVIDIA Deep Learning GPU Training System (DIGITS™) and read the Getting Started with DIGITS blog post.
Developers and Researchers: Choose one of these widely-used open source deep learning frameworks accelerated by the Deep Learning SDK.
A deep learning framework made with expression, speed, and modularity in mind. Caffe is developed by the Berkeley Vision and Learning Center (BVLC), as well as community contributors. Learn more.
A unified deep-learning toolkit from Microsoft Research that makes it easy to train and combine popular model types across multiple GPUs and servers. Learn more.
A software library for numerical computation using data flow graphs, developed by Google’s Machine Intelligence research organization. Learn more.
A math expression compiler that lets you efficiently define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays. Learn more
A scientific computing framework that offers wide support for machine learning algorithms. Learn more.
3. Get a GPU
- GeForce GTX Titan X - PC graphics card based on the revolutionary NVIDIA Maxwell™ architecture
- DIGITS™ DevBox – a deep learning deskside supercomputer with four TITAN X GPUs & NVIDIA DIGITS Software
- Tesla® M40 – the fastest deep learning training accelerator
- Amazon Web Services G2 GPU instance
- IBM Softlayer GPU Servers
- Jetson TX1 Developer Kit – a full-featured development platform for visual computing embedded applications
- DRIVE™ PX – a self driving car computer based on the NVIDIA® Tegra® X1 processor
For questions or feedback, please email deeplearning@nvidia.com