Students to Beat Google’s Machine-Learning Code

Student programmers' image classification algorithm successfully identifies the object in 93% of cases
13 August 2018   1847

Developers-students from Fast.ai which organize free online computer training courses have created an image classification algorithm that successfully identifies the object in 93% of cases and copes with it faster than a similar Google algorithm with a similar configuration. The authors argue that "the creation of breakthrough technologies is not just for big companies". This is reported by MIT Technology Review.

When evaluating performance, the DAWNBench test was used, which calculates the speed and cost of teaching the neural network. During the Fast.ai experiment, the neural network was launched on 16 virtual AWS nodes, each contained 8 NVIDIA V100 graphics cards. This configuration achieved accuracy of 93% in 18 minutes, and the cost of machine time was estimated at $ 40. The result of Fast.ai is faster than the development of Google engineers by 40%, but the corporation uses its own clusters TPU Pod, so the comparison is not entirely objective.

The developers used the PyTorch Python library, as well as their own development - fastai. They were able to achieve this learning speed with the new method of cropping images from the ImageNet dataset: instead of square pictures, they began to use rectangular:

Fast AI
Fast AI

State-of-the-art results are not the exclusive domain of big companies. These are the obvious, dumb things that many researchers wouldn’t even think to do.
 

Jeremy Howard

Founder, Fast.AI

The authors tried to make the project accessible to everyone, so they simplified its infrastructure, refusing to use distributed computing systems and containers. To implement it, developers teamed up with engineers from the innovative division of the Pentagon (DIU) to release software to quickly create and support distributed models on AWS. 

TensorFlow 2.0 to be Released

New major release of the machine learning platform brought a lot of updates and changes, some stuff even got cut
01 October 2019   172

A significant release of the TensorFlow 2.0 machine learning platform is presented, which provides ready-made implementations of various deep machine learning algorithms, a simple programming interface for building models in Python, and a low-level interface for C ++ that allows you to control the construction and execution of computational graphs. The system code is written in C ++ and Python and is distributed under the Apache license.

The platform was originally developed by the Google Brain team and is used in Google services for speech recognition, facial recognition in photographs, determining the similarity of images, filtering spam in Gmail, selecting news in Google News and organizing the translation taking into account the meaning. Distributed machine learning systems can be created on standard equipment, thanks to the built-in support in TensorFlow for spreading computing to multiple CPUs or GPUs.

TensorFlow provides a library of off-the-shelf numerical computation algorithms implemented through data flow graphs. The nodes in such graphs implement mathematical operations or entry / exit points, while the edges of the graph represent multidimensional data arrays (tensors) that flow between the nodes. The nodes can be assigned to computing devices and run asynchronously, simultaneously processing all the suitable tensors at the same time, which allows you to organize the simultaneous operation of nodes in the neural network by analogy with the simultaneous activation of neurons in the brain.

Get more info about the update at official website.