Duality — A New Approach to Reinforcement Learning
https://ai.googleblog.com/2020/07/duality-new-approach-to-reinforcement.html
https://ai.googleblog.com/2020/07/duality-new-approach-to-reinforcement.html
Googleblog
Duality — A New Approach to Reinforcement Learning
One Policy to Control Them All:
Shared Modular Policies for Agent-Agnostic Control
https://wenlong.page/modular-rl/
Shared Modular Policies for Agent-Agnostic Control
https://wenlong.page/modular-rl/
A generative perspective | OATML | Oxford Applied and Theoretical Machine Learning Group
https://oatml.cs.ox.ac.uk/blog/2020/07/10/are-capsules-a-good-idea-a-generative-perspective.html
https://oatml.cs.ox.ac.uk/blog/2020/07/10/are-capsules-a-good-idea-a-generative-perspective.html
oatml.cs.ox.ac.uk
Are capsules a good idea? A generative perspective - OATML
I’ve recently written a paper on a fully probabilistic version of capsule networks. While trying to get this kind of model to work, I found some interesting conceptual issues with the ideas underlying capsule networks. Some of these issues are a bit philosophical…
Fiddler & Captum join hands to enhance Explainable AI offerings
https://medium.com/pytorch/fiddler-captum-join-hands-to-enhance-explainable-ai-offerings-2d92beac2b86
https://medium.com/pytorch/fiddler-captum-join-hands-to-enhance-explainable-ai-offerings-2d92beac2b86
Medium
Fiddler & Captum join hands to enhance Explainable AI offerings
We are excited to announce that Fiddler and Captum are collaborating to push the boundaries of Explainable AI.
⚡️23 июля в 20:00 состоится демо-урок «Логистическая регрессия для классификации данных».
За 1,5 часа вы:
● Обсудите основы регрессионных моделей
● Узнаете, как устроена логистическая регрессия
● Разберёте, какие разделы математики используются для ее построения
● Поймёте, как улучшить этот классификатор.
Занятие является частью курса «Математика для Data Science. Продвинутый уровень». Приходите получить полезные знания, познакомиться с преподавателем и оценить формат обучения.
👉Для регистрации пройдите вступительный тест, который поможет сориентироваться в уровне вашей подготовки: https://otus.pw/f6bb/
За 1,5 часа вы:
● Обсудите основы регрессионных моделей
● Узнаете, как устроена логистическая регрессия
● Разберёте, какие разделы математики используются для ее построения
● Поймёте, как улучшить этот классификатор.
Занятие является частью курса «Математика для Data Science. Продвинутый уровень». Приходите получить полезные знания, познакомиться с преподавателем и оценить формат обучения.
👉Для регистрации пройдите вступительный тест, который поможет сориентироваться в уровне вашей подготовки: https://otus.pw/f6bb/
Building a REST API with Tensorflow Serving (Part 1)
https://www.kdnuggets.com/2020/07/building-rest-api-tensorflow-serving-part-1.html
https://www.kdnuggets.com/2020/07/building-rest-api-tensorflow-serving-part-1.html
KDnuggets
Building a REST API with Tensorflow Serving (Part 1) - KDnuggets
Part one of a tutorial to teach you how to build a REST API around functions or saved models created in Tensorflow. With Tensorflow Serving and Docker, defining endpoint URLs and sending HTTP requests is simple.
Drone Face Tracking PID using OpenCV p.1
https://www.murtazahassan.com/drone-face-tracking-pid-using-opencv-p-1/
https://www.murtazahassan.com/drone-face-tracking-pid-using-opencv-p-1/
Add Binary Flags for Missing Values for Machine Learning
https://machinelearningmastery.com/binary-flags-for-missing-values-for-machine-learning/
https://machinelearningmastery.com/binary-flags-for-missing-values-for-machine-learning/
Consensus-Aware Visual-Semantic Embedding (CVSE)
Github: https://github.com/BruceW91/CVSE
Paper: https://arxiv.org/abs/2007.08883
Github: https://github.com/BruceW91/CVSE
Paper: https://arxiv.org/abs/2007.08883
DeepMind’s AI automatically generates reinforcement learning algorithms
https://venturebeat.com/2020/07/20/deepminds-ai-automatically-generates-reinforcement-learning-algorithms/
https://venturebeat.com/2020/07/20/deepminds-ai-automatically-generates-reinforcement-learning-algorithms/
VentureBeat
DeepMind’s AI automatically generates reinforcement learning algorithms
Researchers at DeepMind propose a new technique that automatically discovers a reinforcement learning algorithm from scratch.
Learning perturbation sets for robust machine learning
Git: https://locuslab.github.io/2020-07-20-perturbation/
Code: https://github.com/locuslab/perturbation_learning
Paper: https://arxiv.org/abs/2007.08450
Git: https://locuslab.github.io/2020-07-20-perturbation/
Code: https://github.com/locuslab/perturbation_learning
Paper: https://arxiv.org/abs/2007.08450
locuslab.github.io
Learning perturbation sets for robust machine learning
Using generative modeling to capture real-world transformations from data for adversarial robustness
Accelerating TensorFlow Lite with XNNPACK Integration
https://blog.tensorflow.org/2020/07/accelerating-tensorflow-lite-xnnpack-integration.html
https://blog.tensorflow.org/2020/07/accelerating-tensorflow-lite-xnnpack-integration.html
blog.tensorflow.org
Accelerating TensorFlow Lite with XNNPACK Integration
Leveraging the CPU for ML inference yields the widest reach across the space of edge devices. Consequently, improving neural network inference performance on CPUs has been among the top requests to the TensorFlow Lite team. We listened and are excited to…
Deep learning to translate between programming languages
https://ai.facebook.com/blog/deep-learning-to-translate-between-programming-languages
https://ai.facebook.com/blog/deep-learning-to-translate-between-programming-languages
Meta
Deep learning to translate between programming languages
TransCoder is the first self-supervised neural transcompiler system for migrating code between programming languages. It can translate code from Python to C++, for example, and it outperforms rule-based translation programs.