Is it possible to use machine learning without needing to code? The answer is yes! Uber's AI lab recently open sourced python library called Ludwig that they've been using internally for 2 years. The tagline is that it allows anyone to use deep learning without…

A simple explanation of how they work and how to implement one from scratch in Python.

Notes from the Frontiers of Machine Perfection

Традиционными инструментами в сфере Data Science являются такие языки, как R и Python — расслабленный синтаксис и большое количество библиотек для машинного обу...

Interpretability techniques to build robust, unbiased AI applications

An artificial-intelligence “artist” got a solo show at a Chelsea gallery. Will it reinvent art, or destroy it?

Syndicated from Springboard.

Games have been used for decades as an important way to test and evaluate the performance of artificial intelligence systems. As capabilities have increased, the research community has sought...

This post gives an intuitive explanation of an approach called Natural Gradient, an elegant way to dynamically adjust gradient step size.

When learning to code for data science we don’t usually consider the idea of modifying our code to reap a particular benefit in terms of…

An introduction to RNN and LSTM networks, as well as their applications.

A method you should try when you have data of low granularity with recurring local pattern

📝 The paper " GAN Dissection: Visualizing and Understanding Generative Adversarial Networks " and its web demo is available here:
https://gandissect.csail.mit.edu
https://gandissect.res.ibm.com/ganpaint.html

❤️ Pick up cool perks on our Patreon page: htt…

The field of computer vision is shifting from statistical methods to deep learning neural network methods. There are still many challenging problems to solve in computer vision. Nevertheless, deep learning methods are achieving state-of-the-art results on…

(i.e. how to explain machine learning algorithms to your grandma)

Widely, there are two categories of people. One, as soon as you read the title of this article, you would readily assume that AI cannot…

Most machine learning systems require the ability to explain to stakeholders why certain predictions are made. When choosing a suitable…

Neural architecture search (NAS) is the process of algorithmically searching for new designs of neural networks. Though researchers have…