In this article, I will talk about the Kernel and Nearest Neighbor Approach which forms a major class of non-parametric methods to solve a…

Public datasets fuel the machine learning research rocket (h/t Andrew Ng), but it’s still too difficult to simply get those datasets into…

Speech recognition is a fun task. A lot of API resources are available in market today which makes it easier for user to opt for one or…

Jupyter notebook with Pytorch implementation of Neural Ordinary Differential Equations - msurtsukov/neural-ode

Aleksandra Faust, Senior Research Scientist and Anthony Francis, Senior Software Engineer, Robotics at Google In the United States alone, there are...

Master Deep Learning and Computer Vision with PyTorch - Full Course on sale for $10! (normally $200):

https://www.udemy.com/pytorch-for-deep-learning-and-computer-vision/?couponCode=PYTORCHYOUTUBE09

PyTorch has rapidly become one of the most transformative…

Gradient boosting has become quite a popular technique in the area of machine learning. Given its reputation for achieving potentially…

Директор по аналитике больших данных в «МегаФон» Виталий Щербаков рассказал о том, как происходит сбор и аналитика больших данных, как построить предсказательную модель поведения пользователей и как устроиться на работу в компанию. В конце ролика, по традиции…

Remembering what’s important

From creating datasets to testing your program accuracy

A very quick introduction to building a foundation in probability theory for understanding machine/deep learning

Искусственный интеллект: как он есть и каким он должен быть.

По определению, к задачам искусственного интеллекта относятся все задачи, не имеющие точного алгоритмического решения.

Вот и давайте поговорим про нейронные сети, генетические алгоритмы, задачи…

Information Theory

Supervised machine learning is often described as the problem of approximating a target function that maps inputs to outputs.

This denoscription is characterized as searching through and evaluating candidate hypothesis from hypothesis spaces.

The discussion…

A guide to the less desirable aspects of deep learning environment configurations

Few months ago I mentioned some of the exciting new features that will be included in TensorFlow 2.0.

Skills in deep learning are in great demand, although these skills can be challenging to identify and to demonstrate.

Explaining that you are familiar with a technique or type of problem is very different to being able to use it effectively with open source…