News
News Categories

Google is bringing you smarter machine learning with TensorFlow

By Marcus Wong - on 11 Nov 2015, 2:35pm

Google is bringing you smarter machine learning with TensorFlow

Deep learning is not new to Google, as they’ve been developing their own internal deep learning infrastructure (DistBelief) since before 2011. DistBelief has powered Google’s experiments in automated image captioning and their research into neural networks like DeepDream.

In Google’s own words, DistBelief had some limitations. It was narrowly targeted to neural networks, it was difficult to configure, and it was tightly coupled to Google’s internal infrastructure - making it nearly impossible to share research code externally. And that’s where TensorFlow comes in.

Google’s second-generation machine learning system is specifically designed to be general, flexible, portable, easy-to-use and completely open-source. That’s a key point because it means anyone from academic researchers to hobbyists to software engineers will be able to contribute to the development of TensorFlow and machine learning in general, accelerating the development process.

Because TensorFlow is also built to be very general, any computation that can be expressed as a computational flow graph can be computed with TensorFlow, and any gradient-based machine learning algorithm will be able to tap into TensorFlow’s auto-differentiation and first rate optimizers. Google says TensorFlow is available as a standalone library with the associated tools, tutorials and examples with an Apache 2.0 license so you can jump right into development.

Here’s an example of how you can adapt TensoFlow to compute computational flow graphs (animated gif):

And here’s a video overview on TensoFlow:

Otherwise, if you really want to dive into it, you can take a look at the white paper here.

Source: Google Blog

Join HWZ's Telegram channel here and catch all the latest tech news!
Our articles may contain affiliate links. If you buy through these links, we may earn a small commission.