Deep Learning and Reinforcement Learning Summer School, Toronto 2018
video:
http://videolectures.net/DLRLsummerschool2018_toronto/
video:
http://videolectures.net/DLRLsummerschool2018_toronto/
videolectures.net
Deep Learning and Reinforcement Learning Summer School, Toronto 2018
Deep neural networks are a powerful method for automatically learning distributed representations at multiple levels of abstraction. Over the past decade, they have dramatically pushed forward the state-of-the-art in domains as diverse as vision, language…
Curiosity and Procrastination in Reinforcement Learning
https://ai.googleblog.com/2018/10/curiosity-and-procrastination-in.html
https://ai.googleblog.com/2018/10/curiosity-and-procrastination-in.html
research.google
Curiosity and Procrastination in Reinforcement Learning
Posted by Nikolay Savinov, Research Intern, Google Brain Team and Timothy Lillicrap, Research Scientist, DeepMind Reinforcement learning (RL) is on...
How to analyze “Learning”: Short tour of Computational Learning Theory
https://towardsdatascience.com/how-to-analyze-learning-short-tour-of-computational-learning-theory-9d93b15fc3e5
https://towardsdatascience.com/how-to-analyze-learning-short-tour-of-computational-learning-theory-9d93b15fc3e5
Medium
Reaching for the gut of Machine Learning: A brief intro to CLT
Knowing the fundamentals of the computational learning theory can empower you immensely as a practitioner of machine learning.
Playing Mortal Kombat with TensorFlow.js. Transfer learning and data augmentation
https://blog.mgechev.com/2018/10/20/transfer-learning-tensorflow-js-data-augmentation-mobile-net/
https://blog.mgechev.com/2018/10/20/transfer-learning-tensorflow-js-data-augmentation-mobile-net/
Mgechev
Playing Mortal Kombat with TensorFlow.js. Transfer learning and data augmentation
While experimenting with enhancements of the prediction model of Guess.js, I started looking at deep learning. I’ve focused mainly on recurrent neural networks (RNNs), specifically LSTM because of their “unreasonable effectiveness” in the domain of Guess.js.…
Dimensionality Reduction For Dummies — Part 2: Laying The Bricks
https://towardsdatascience.com/data-science/home
https://towardsdatascience.com/data-science/home
Towards Data Science
Data Science – Towards Data Science
Towards Data Science provides a platform for thousands of people to exchange ideas and to expand our understanding of data science. Your home for data science. A publication sharing concepts, ideas and codes.
Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees
https://ai.googleblog.com/2018/10/introducing-adanet-fast-and-flexible.html
https://ai.googleblog.com/2018/10/introducing-adanet-fast-and-flexible.html
Googleblog
Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees
Semantic Segmentation of Seismic Reflection Images
https://nikolasent.github.io/deeplearning/competitions/2018/10/24/Semantic-Segmentation-of-Seismic-Reflection-Images.html
https://nikolasent.github.io/deeplearning/competitions/2018/10/24/Semantic-Segmentation-of-Seismic-Reflection-Images.html
Facebook open sourced Horizon, an end-to-end applied reinforcement learning platform built on #PyTorch 1.0. Horizon uses RL to optimize systems in large-scale production environments and we're excited to make it accessible to anyone using #RL at scale.
https://code.fb.com/ml-applications/horizon/
https://code.fb.com/ml-applications/horizon/
Engineering at Meta
Horizon: The first open source reinforcement learning platform for large-scale products and services
An end-to-end platform built on PyTorch 1.0 that is designed to jump start RL’s transition from research papers to production
❤1
Applying Machine Learning to classify an unsupervised text document
https://towardsdatascience.com/applying-machine-learning-to-classify-an-unsupervised-text-document-e7bb6265f52
https://towardsdatascience.com/applying-machine-learning-to-classify-an-unsupervised-text-document-e7bb6265f52
Medium
Applying Machine Learning to classify an unsupervised text document
Text classification is a problem where we have fixed set of classes/categories and any given text is assigned to one of these categories…
Building client routing / semantic search and clustering arbitrary external corpuses at Profi.ru
https://habr.com/post/428674/
https://habr.com/post/428674/
Хабр
Building client routing / semantic search at Profi.ru
Building client routing / semantic search and clustering arbitrary external corpuses at Profi.ru TLDR This is a very short executive summary (or a teaser) about...
The MAME RL Algorithm Training Toolkit
This Python library has the to potential to train your reinforcement learning algorithm on almost any arcade game. It is currently available on Linux systems and works as a wrapper around MAME. The toolkit allows your algorithm to step through gameplay while recieving the frame data and internal memory address values for tracking the games state, along with sending actions to interact with the game.
https://github.com/M-J-Murray/MAMEToolkit
This Python library has the to potential to train your reinforcement learning algorithm on almost any arcade game. It is currently available on Linux systems and works as a wrapper around MAME. The toolkit allows your algorithm to step through gameplay while recieving the frame data and internal memory address values for tracking the games state, along with sending actions to interact with the game.
https://github.com/M-J-Murray/MAMEToolkit
GitHub
GitHub - M-J-Murray/MAMEToolkit: A Python toolkit used to train reinforcement learning algorithms against arcade games
A Python toolkit used to train reinforcement learning algorithms against arcade games - M-J-Murray/MAMEToolkit
👍1
PyTorch implementation of Google AI's BERT model with a noscript to load Google's pre-trained models
https://github.com/huggingface/pytorch-pretrained-BERT
https://github.com/huggingface/pytorch-pretrained-BERT
GitHub
GitHub - huggingface/transformers: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models…
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. - GitHub - huggingface/t...
Using 3D visualizations to tune hyperparameters in ML models
https://towardsdatascience.com/using-3d-visualizations-to-tune-hyperparameters-of-ml-models-with-python-ba2885eab2e9
https://towardsdatascience.com/using-3d-visualizations-to-tune-hyperparameters-of-ml-models-with-python-ba2885eab2e9
Medium
Using 3D visualizations to tune hyperparameters of ML models with Python
Visualizing validation curves can be tricky when we have more than 1 hyperparameter. Here’s how to do it when we have 2, 3 and even more.
Artificial Intelligence meets Art: Neural Transfer Style
https://towardsdatascience.com/artificial-intelligence-meets-art-neural-transfer-style-50e1c07aa7f7
https://towardsdatascience.com/artificial-intelligence-meets-art-neural-transfer-style-50e1c07aa7f7
Medium
Artificial Intelligence meets Art: Neural Transfer Style
Introduction