Как вычислить замыслы киберпреступников, атакующих промышленный объект и распознать слабые сигналы SOS, которые периодически подает индустриальная АСУ ТП на...

Перевод поста Филиппа Ходжетта, выступавшего недавно на конференции Hollywood Professional Association Tech Retreat. Надеюсь, собранный в одном месте список...

Изложение статьи от том, что давно известные эволюционные стратегии оптимизации могут превзойти алгоритмы обучения с подкреплением. Преимущества эволюционных...

Deep learning neural networks are very easy to create and evaluate in Python with Keras, but you must follow a strict model life-cycle.

In this post, you will discover the step-by-step life-cycle for creating, training, and evaluating Long Short-Term Memory…

An adversarial example library for constructing attacks, building defenses, and benchmarking both - cleverhans-lab/cleverhans

Code for "On the Effects of Batch and Weight Normalization in Generative Adversarial Networks" - stormraiser/GAN-weight-norm

Counting Objects with Faster R-CNN. Accurately counting objects instances is a hard problem to solve in machine learning.

Performing anomaly detection using a recurrent neural network to find the ugliest flamingos in a dataset of sketches.

Build a neural network that learns to generate handwritten digits.

Gradient boosting is attracting attention for its prediction speed & accuracy, especially with large & complex data. Learn about gradient boosting here.

For a while now I’ve been experimenting with ways to use generative neural nets to make portraits. Early experiments were based on deepdream-like approaches ...

Disclaimer:

A lecture introducing Variational Inference and Deep Learning. Adapted from a lecture I gave for Aaron Courville's Deep Learning course (IFT 6266).

Combining the world’s most popular sport with everyone’s favourite discrete probability distribution, this post predicts football matches using the Poisson distribution.