​Искусственный интеллект и консервативные индустрии. История успешного внедрения на металлургическом заводе

🔗 Искусственный интеллект и консервативные индустрии. История успешного внедрения на металлургическом заводе
Искусственный интеллект в промышленности Часто люди, работающие в области технологий искусственного интеллекта, представляют себе металлургический завод как неч...

​У искусственного интеллекта найден инстинкт размножения

🔗 У искусственного интеллекта найден инстинкт размножения
Наша команда из почти ста человек, занимающихся обучением нейросетей, постоянно сокращается, потому что нейросети начали обучать себя сами. А недавно и материал...

​Почему стриминг на KSQL и Kafka Streams — это непросто

🔗 Почему стриминг на KSQL и Kafka Streams — это непросто
Привет, Хабр! Меня зовут Саша, я лид-разработчик в GlowByte Consulting. Мы с командой сделали неплохой стриминговый движок для одного крупного банка. Сейчас в п...

​Нейросеть — Обучение без учителя. Метод Policy Gradient

🔗 Нейросеть — Обучение без учителя. Метод Policy Gradient
Доброго времени суток Хабр. Настоящей статьей открываю цикл статей о том, как обучать нейронные сети без учителя. (Reinforcement Learning for Neuron Networks)...

​Abstractive Text Summarization Using Transformers

🔗 Abstractive Text Summarization Using Transformers
An exhaustive explanation of Google’s Transformer model; from theory to implementation

​Bayesian Graph Neural Networks with Adaptive Connection Sampling https://arxiv.org/abs/2006.04064

🔗 Bayesian Graph Neural Networks with Adaptive Connection Sampling
We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs. The proposed framework not only alleviates over-smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs. Instead of using fixed sampling rates or hand-tuning them as model hyperparameters in existing stochastic regularization methods, our adaptive connection sampling can be trained jointly with GNN model parameters in both global and local fashions. GNN training with adaptive connection sampling is shown to be mathematically equivalent to an efficient approximation of training Bayesian GNNs. Experimental results with ablation studies on benchmark datasets validate that adaptively learning the sampling rate given graph training data is the key to boost the performance of GNNs in semi-supervised node classification, less prone to over-smoothing and over-fitting with m

​Unsupervised Reinforcement Learning

🔗 Unsupervised Reinforcement Learning
Watch Sergey Levine's lecture at International Conference on Autonomous Agents and Multi-Agent Systems 2020

​Efficient PyTorch — Part 1

🔗 Efficient PyTorch — Part 1
What is an efficient training pipeline? Is it the one, that produces a model with the best accuracy? Or the one that runs the fastest? Or…

​How to Set Up Docker for Deep Learning on AWS

🔗 How to Set Up Docker for Deep Learning on AWS
Access GPUs inside a running container with nvidia-docker

​Ordinal and One-Hot Encodings for Categorical Data - Machine Learning Mastery

🔗 Ordinal and One-Hot Encodings for Categorical Data - Machine Learning Mastery
Machine learning models require all input and output variables to be numeric. This means that if your data contains categorical data, you must encode it to numbers before you can fit and evaluate a model. The two most popular techniques are an Ordinal Encoding and a One-Hot Encoding. In this tutorial, you will discover how to use encoding schemes for categorical machine learning

​A 12nm Programmable Convolution-Efficient Neural-Processing-Unit Chip Achieving 825TOPS

https://ieeexplore.ieee.org/document/9062984

🔗 7.2 A 12nm Programmable Convolution-Efficient Neural-Processing-Unit Chip Achieving 825TOPS - IEEE C
IEEE Xplore, delivering full text access to the world's highest quality technical literature in engineering and technology. | IEEE Xplore

​Quick Uncertainty Estimates for COVID19 Excess Mortality

🔗 Quick Uncertainty Estimates for COVID19 Excess Mortality
For a recent story The Economist has gathered large amounts of time series data to perform COVID “excess deaths” analysis per country.

​Linear Regression with PyTorch

🔗 Linear Regression with PyTorch
After reading this article you will have knowledge of how to implement linear regression with PyTorch Library with an example.

🎥 Случайный лес
👁 1 раз ⏳ 367 сек.
Запишетесь на полный курс Машинного обучения на Python по адресу support@ittensive.com

🎥 SIMPLIFY Data Analytics and Machine Learning Made Simple
👁 1 раз ⏳ 3718 сек.
The main goal of the session is to showcase approaches that greatly simplify the work of a data analyst when performing data analytics, or when employing machine learning algorithms, over Big Data. The session will include presentations on

(a) How data analytics workflows can be easily and graphically composed, and then optimized for execution,

(b) How raw data with great variety can be easily queried using SQL interfaces, and

(c) How complex machine learning operations can be performed efficiently in di

🎥 Deep Learning Training in Trichy Part 10 | Artificial Neural Network |11 june 2020 |9789888424
👁 1 раз ⏳ 5478 сек.
Introduction to Deep Learning
Artificial Neural Network

contact details: 9789888424(Kaleel Ahamed)
Time : 6.30 am - 7.30 am (Indian Time)
Date and time : June 6th to June 14th 2020
Whats App-9789888424
Trainer : Irfan /Dinesh / Kaleel

Kindly use the below link to connect.
https://us04web.zoom.us/j/8301787301
Meeting id will be 8301787301

Join our What app group to get the regular updates:
https://chat.whatsapp.com/HfdRIm9lZm08uJvXHzis6C

DAY 1
Introduction to Deep Learning
Artificial Neural Network

DAY

​StyleGAN2: AI’s Imagination

🔗 StyleGAN2: AI’s Imagination
For better understanding of StyleGAN2s capabilities and how it works, we are going to use use them to generate images in different…

​Music genre analysis — Understanding emotions and topics in different genres

🔗 Music genre analysis — Understanding emotions and topics in different genres
Understanding the topics in different music genres and creating simple applications for predictions and recommendations

🎥 Simple way of learning Machine Learning, Artificial Neural Network, Deep Learning in Excel.
👁 1 раз ⏳ 3195 сек.
I explained step by step how to calculate Artificial Neural Network forward and back propagation in Excel. You don't need any programming skill.
To understand easily I removed bias'es.
If you want to add bias, just add another neurons like the others with the value 1. To add a bias to the 3,4, 5 and 6. neurons:
2 neuron names may be: hb345=1;hb6=1;
Add weights with the names like wb3, wb4,wb5, wb6:
the inputs of hidden layer's neuron's equations should be like:
n3=h1*w13+h2*w23+hb345*wb3;
n4=h1*w14+h2*w24+

📃 Огромная библиотека DS книг-

Огромная библиотека DS книг- https://xn--r1a.website/datascienceiot Data Science t.me