Reinforcement Learning

Let's say we have an agent in an unknown environment and this agent can obtain some rewards by interacting with the environment.

The agent is tasked to take actions so as to maximize cumulative rewards. In reality, the scenario could be a bot playing a game to achieve high scores, or a robot trying to complete physical tasks with physical items; and not just limited to these.

Like humans, RL agents learn for themselves to achieve successful strategies that lead to the greatest long-term rewards.

This kind of learning by trial-and-error, based on rewards or punishments, is known as reinforcement learning (RL).

TensorTrade is an open-source Python framework for building, training, evaluating, and deploying robust trading algorithms using reinforcement learning.

https://github.com/tensortrade-org/tensortrade

#artificialintelligence #machinelearning #datascience #datascience #python

🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python

Big GANs Are Watching

You It is the state-of-the-art unsupervised GAN, which parameters are publicly available. They demonstrate that object saliency masks for GAN-produced images can be obtained automatically with BigBiGAN. These masks then are used to train a discriminative segmentation model. Being very simple and easy-to-reproduce, our approach provides competitive performance on common benchmarks in the unsupervised scenario.

Github: https://github.com/anvoynov/BigGANsAreWatching

Paper : https://arxiv.org/abs/2006.04988

#datascience #machinelearning #artificialintelligence #deeplearning

Google Research • Representation Learning for Information Extraction from Templatic Documents such as receipts, bills, insurance quotes. We propose a novel approach using representation learning for tackling the problem of extracting structured information from form-like document images.

Blogpost

https://ai.googleblog.com/2020/06/extracting-structured-data-from.html?m=1

Paper

https://research.google/pubs/pub49122/
We propose an extraction system that uses knowledge of the types of the target fields to generate extraction candidates, and a neural network architecture that learns a dense representation of each candidate based on neighboring words in the document. These learned representations are not only useful in solving the extraction task for unseen document templates from two different domains, but are also interpretable, as we show using loss cases. #machinelearning #deeplearning #datascience #dataengineer #nlp

Google Research • Representation Learning for Information Extraction from Templatic Documents such as receipts, bills, insurance quotes. We propose a novel approach using representation learning for tackling the problem of extracting structured information from form-like document images.

Blogpost

https://ai.googleblog.com/2020/06/extracting-structured-data-from.html?m=1

Paper

https://research.google/pubs/pub49122/
We propose an extraction system that uses knowledge of the types of the target fields to generate extraction candidates, and a neural network architecture that learns a dense representation of each candidate based on neighboring words in the document. These learned representations are not only useful in solving the extraction task for unseen document templates from two different domains, but are also interpretable, as we show using loss cases. #machinelearning #deeplearning #datascience #dataengineer #nlp

Lecture Notes in Deep Learning: Feedforward Networks — Part 3 | #DataScience #MachineLearning #ArtificialIntelligence #AI

https://bit.ly/2Z2GgQY