​Improving Evolutionary Strategies with Generative Neural Networks

https://arxiv.org/abs/1901.11271

🔗 Improving Evolutionary Strategies with Generative Neural Networks
Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of objective functions. This paper investigates the potential benefits of using highly flexible search distributions in classical ES algorithms, in contrast to standard ones (typically Gaussians). We model such distributions with Generative Neural Networks (GNNs) and introduce a new training algorithm that leverages their expressiveness to accelerate the ES procedure. We show that this tailored algorithm can readily incorporate existing ES algorithms, and outperforms the state-of-the-art on diverse objective functions.

​Article Image
Understanding Neural ODE's

https://jontysinai.github.io/jekyll/update/2019/01/18/understanding-neural-odes.html

🔗 Understanding Neural ODE's
In this blogpost I explore how ODE’s can be used to solve data modelling problems. I take a deep dive into the data modelling problem at hand and present ODE’s (which model rates of change) as an a...

​Maximum Likelihood Estimation

🔗 Maximum Likelihood Estimation – Towards Data Science
Fundamentals of Machine Learning (Part 2)

Unmaking Graphs
https://towardsdatascience.com/unmaking-graphs-f584625c5bfd?source=collection_home---4------1---------------------

​Building a Neural Network Only Using NumPy

🔗 Building a Neural Network Only Using NumPy – Lukas Frei – Medium
Using Andrew Ng’s Project Structure to Build a Neural Net in Python

​Can neural networks learn commonsense reasoning?

ATOMIC | An Atlas of Machine Commonsense for If-Then Reasoning: https://homes.cs.washington.edu/~msap/atomic/

🔗 ATOMIC Knowledge Graph Browser

Making deep neural networks paint to understand how they work
https://towardsdatascience.com/making-deep-neural-networks-paint-to-understand-how-they-work-4be0901582ee?source=collection_home---4------0---------------------

​Machine Learning Tutorial Python - 13: K Means Clustering

🔗 Machine Learning Tutorial Python - 13: K Means Clustering
Code: https://github.com/codebasics/py/blob/master/ML/13_kmeans/13_kmeans_tutorial.ipynb K Means algorithm is unsupervised machine learning technique used to...

​Amazon AI Conclave 2018 - How to Speed up Deep Learning training and inferencing by Thomas Delteil

🔗 Amazon AI Conclave 2018 - How to Speed up Deep Learning training and inferencing by Thomas Delteil
How to speed up Deep Learning training and inferencing,cutting cost and improving performance' by Thomas Delteil, Machine Learning Scientist, AWS Amazon AI C...

​Making Friends with Machine Learning: Regression

🔗 Making Friends with Machine Learning: Regression
Make friends with the amazing power of machine learning! In this video, Cassie walks you through machine learning terminology and basic concepts by applying ...

​AAAI Conference Analytics

Citation distribution by the top AAAI 20 authors, year by year:

#artificalintelligence #deeplearning #machinelearning

🔗 Microsoft Power BI

​Data Management Systems

Access more info http://bit.ly/2RDEvUm

The global data management system (DBMS) market is expected to witness growth over the computer system. It is an extensive process for the development of data processing facilities. In this case, it is possible to solve the problem.

🔗 Data Management System Market | DBMS Industry Report, 2022
Data Management System (DBMS) market is anticipated to witness growth over the forecast period owing to widespread use of computer system

​После 18-го февраля начнется открытый и бесплатный курс "Deep Learning на пальцах".

https://habr.com/ru/company/ods/blog/438940/
Наш телеграмм канал - https://t.me/ai_machinelearning_big_data

Курс предназначен для того, чтобы разобраться с современным deep learning с нуля, и не требует знаний ни нейросетей, ни machine learning вообще. Лекции стримами на Youtube, задания на Питоне, обсуждения и помощь в лучших русскоязычных чат-сообществах — ODS.ai и ClosedCircles.

После него вы не станете экспертом, но поймете про что все это, сможете применять DL на практике и будете способны разбираться дальше сами. Ну, в лучшем случае.

Одновременно и в том же объеме курс будет читаться для магистрантов Новосибирского Государственного Университета, а также студентов CS центра Новосибирска.

Выглядеть объяснение на пальцах будет примерно так:

🔗 Открытый курс «Deep Learning на пальцах»
После 18-го февраля начнется открытый и бесплатный курс "Deep Learning на пальцах". Курс предназначен для того, чтобы разобраться с современным deep learning с...

​AI пати в Siliconовой Долине: мэр, миллиардер, президенты, гении, разработчики процессоров и девушка с яркими волосами

https://habr.com/ru/post/438928/

🔗 AI пати в Siliconовой Долине: мэр, миллиардер, президенты, гении, разработчики процессоров и девушка
В прошлом году в российской и украинской прессе прошла волна статей о вечеринках в Кремниевой долине, с какой-то голливудской атмосферностью, но без указания...

​Amazon AI Conclave 2018 - How to Speed up Deep Learning training and inferencing by Thomas Delteil

🔗 Amazon AI Conclave 2018 - How to Speed up Deep Learning training and inferencing by Thomas Delteil
How to speed up Deep Learning training and inferencing,cutting cost and improving performance' by Thomas Delteil, Machine Learning Scientist, AWS Amazon AI C...

Why do spectrogram-based VGGs rock?
https://towardsdatascience.com/why-do-spectrogram-based-vggs-rock-6c533ec0235c?source=collection_home---4------1---------------------

Learning Machine Learning with .NET, PyTorch and the ONNX Runtime

🎥 Learning Machine Learning with .NET, PyTorch and the ONNX Runtime
👁 1 раз ⏳ 1700 сек.
ONNX is a open format to represent deep learning models that is supported by various frameworks and tools. This format makes it easier to interoperate between frameworks and to maximize the reach of your hardware optimization investments

In this episode, Seth Juarez (@sethjuarez) sits with Rich to show us how we can use the ONNX runtime inside of our .NET applications. He gives us a quick introduction to training a model with PyTorch, and also explains some foundational concepts around prediction accuracy.

https://habr.com/ru/post/438886/

Морти, мы в UltraHD! Как посмотреть любой фильм в 4K, дорисовав его через малоизвестную нейросеть

#machinelearning #neuralnets #deeplearning #машинноеобучение

Наш телеграмм канал - https://t.me/ai_machinelearning_big_data

The keys of Deep Learning in 100 lines of code
https://towardsdatascience.com/the-keys-of-deep-learning-in-100-lines-of-code-907398c76504?source=collection_home---4------0---------------------

​Gradient Descent, Step-by-Step

🔗 Gradient Descent, Step-by-Step
Gradient Descent is the workhorse behind most of Machine Learning. When you fit a machine learning method to a training dataset, you're probably using Gradie...