While you can train simple neural networks with relatively small amounts of training data with TensorFlow, for deep neural networks with large training datasets you really need to use CUDA-capable Nvidia GPUs, or Google TPUs, or FPGAs for acceleration. The alternative has, until recently, been to train on clusters of CPUs for weeks.

One of the innovations introduced with TensorFlow 2.0 is a JavaScript implementation, TensorFlow.js. I wouldn’t have expected that to improve training or inference speed, but it does, given its support for all GPUs (not just CUDA-capable GPUs) via the WebGL API.

[ Also on InfoWorld: TensorFlow

Nvidia today revealed its latest line of graphics cards, called the RTX 30 series. With three new cards on the way, two of them relatively inexpensive, Nvidia promises they’ll be the next step-up for PC gaming — and from what we’ve seen, it certainly looks like it can back up that claim.

The specs for the GPUs were, by and large, leaked ahead of time, but seeing them in the flesh (figuratively speaking) was still a treat. The star of the show was the RTX 3080, powered by its new Ampere architecture. Nvidia CEO Jensen Huang revealed the card and