Bayesian optimization in PyTorch. Contribute to pytorch/botorch development by creating an account on GitHub.

Posted by Bingyi Cao and Tobias Weyand, Software Engineers, Google AI Last year we released Google-Landmarks, the largest world-wide landmark rec...

It is challenging to know how to best prepare image data when training a convolutional neural network. This involves both scaling the pixel values and use of image data augmentation techniques during both the training and evaluation of the model. Instead…

This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of...

Специалистам по распознаванию речи давно не хватало большого открытого корпуса устной русской речи, поэтому только крупные компании могли позволить себе заниматься этой задачей, но они не...

Written by Óscar D. Lara Yejas and Ankit Jha

В этот раз выбрана игра «Змейка». Создана библиотека для нейросети на языке Go. Найден принцип обучения, зависимый от «глубины» памяти. Написан сервер для игр...

Posted by Vittorio Ferrari, Research Scientist, Machine Perception In 2016, we introduced Open Images, a collaborative release of ~9 million imag...

Achieve high text classification accuracy with smaller datasets.

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training models to perform...

Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without...

TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow - tensorflow/graphics

In complex transfer learning scenarios new tasks might not be tightly linked
to previous tasks. Approaches that transfer information contained only in the
final parameters of a source model will...

This paper presents a new Unified pre-trained Language Model (UniLM) that can
be fine-tuned for both natural language understanding and generation tasks. The
model is pre-trained using three types...