Нейронные сети

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
Нейронные сети 1 Введение
Нейронные сети 2 Немного биологии
Нейронные сети 3 В целом об искусственной нейронной сети 1
Нейронные сети 4 Искусственный нейрон
Нейронные сети 5 Структура нейронной сети
Нейронные сети 6 Нюансы работы нейронной сети
Нейронные сети 7 Обучение сети
Нейронные сети 8 Технология обучения сети Часть 1
Нейронные сети 9 Технология обучения сети Часть 2
Нейронные сети 10 Работа одного нейрона
#ии #Нейронныесети

🎥 Нейронные сети 10 Работа одного нейрона
👁 3348 раз ⏳ 1003 сек.


🎥 Нейронные сети 9 Технология обучения сети Часть 2
👁 1510 раз ⏳ 905 сек.


🎥 Нейронные сети 8 Технология обучения сети Часть 1
👁 1246 раз ⏳ 1367 сек.


🎥 Нейронные сети 7 Обучение сети
👁 1260 раз ⏳ 1077 сек.


🎥 Нейронные сети 6 Нюансы работы нейронной сети
👁 1362 раз ⏳ 1396 сек.


🎥 Нейронные сети 5 Структура нейронной сети
👁 1709 раз ⏳ 905 сек.


🎥 Нейронные сети 4 Искусственный нейрон
👁 1999 раз ⏳ 601 сек.


🎥 Нейронные сети 2 Немного биологии
👁 2862 раз ⏳ 488 сек.


🎥 Нейронные сети 3 В целом об искусственной нейронной сети 1
👁 2724 раз ⏳ 535 сек.
Видео взято с https://www.youtube.com/channel/UC5dqkmvoovlmFsFZ3ACAVTw

🎥 Нейронные сети 1 Введение
👁 6407 раз ⏳ 509 сек.
Видео взято с канала https://www.youtube.com/channel/UC5dqkmvoovlmFsFZ3ACAVTw

🎥 Machine Learning Software Engineering
👁 1 раз ⏳ 1010 сек.
Machine learning is the next generation of software engineering, and this means we need a start a cultural shift towards data scientists becoming active and productive participants in the software engineering process. A key part of this is reducing the friction for data scientists to think about coding “non-interactively” and building models and behavioural tests that can run as part of a DevOps pipeline.

Praneet Solanki from the Azure CAT team has been building out a reference architecture for this patte

🎥 Credit Card Fraud Detection using Machine Learning from Kaggle
👁 1 раз ⏳ 1114 сек.
The Credit Card Fraud Detection Problem includes modeling past credit card transactions with the knowledge of the ones that turned out to be fraud. This model is then used to identify whether a new transaction is fraudulent or not.

Github Url: https://github.com/krishnaik06/Credit-Card-Fraudlent

Data Science Interview Question playlist: https://www.youtube.com/watch?v=820Qr4BH0YM&list=PLZoTAELRMXVPkl7oRvzyNnyj1HS4wt2K-

Data Science Projects playlist: https://www.youtube.com/watch?v=5Txi0nHIe0o&list=PLZoT

🎥 PyMC3 — Bayesian Statistical Modelling in Python / PyDaCon
👁 1 раз ⏳ 1832 сек.
22 июня Mail.ru Group прошел совместный митап с организаторами конференции PyCon Russia.

Вас ждут 2 секции: доклады по Python, состав которого был сформирован на основе общего списка докладов к PyCon Russia и PyData-трек от PyData Moscow meetup.

«PyMC3 — Bayesian Statistical Modelling in Python»
Максим Кочуров, PyMC Dev / Samsung AI / Skoltech

Байесовская статистика в последнее время стала обсуждаться в контексте глубокого обучения. К сожалению, это скрывает главное ее преимущество по сравнению со станд

🎥 CVPR 2019 Oral Session 2-1C: Motion & Biometrics
👁 1 раз ⏳ 5709 сек.
0:00 Learning Optical Flow with Occlusion Hallucination Pengpeng Liu (The Chinese University of Hong Kong)*; Michael Lyu (The Chinese University of Hong Kong); Irwin King (The Chinese University of Hong Kong); Jia Xu (Tencent AI Lab)

5:10 Taking a Deeper Look at the Inverse Compositional Algorithm Zhaoyang Lv (GEORGIA TECH)*; Frank Dellaert (Georgia Tech); James Rehg (Georgia Institute of Technology); Andreas Geiger (MPI-IS and University of Tuebingen)

10:10 Deeper and Wider Siamese Networks for Real-Time

​Innovations in Graph Representation Learning

https://ai.googleblog.com/2019/06/innovations-in-graph-representation.html

🔗 Innovations in Graph Representation Learning
Posted by Alessandro Epasto, Senior Research Scientist and Bryan Perozzi, Senior Research Scientist, Graph Mining Team Relational data r...

🎥 Оформление пайплайна в NLP проекте​ / PyDaCon
👁 1 раз ⏳ 1970 сек.
22 июня Mail.ru Group прошел совместный митап с организаторами конференции PyCon Russia.

Вас ждут 2 секции: доклады по Python, состав которого был сформирован на основе общего списка докладов к PyCon Russia и PyData-трек от PyData Moscow meetup.

«Оформление пайплайна в NLP проекте​»

Виталий Радченко, Data Scientist, YouScan

Сейчас многие компании решают разные NLP-задачи (классификация, чат-боты, кластеризация, вопросное-ответные системы и др.) и с накоплением опыта стали вырабатываться наиболее эффект

​Exploring New York City water tank inspection data.

🔗 Exploring New York City water tank inspection data.
My approach to exploring, analyzing and visualizing real estate data using Python and Plotly.

🎥 Создание чат-бота с искусственным интеллектом на Python
👁 3 раз ⏳ 6301 сек.
Распродажа программ с гарантией трудоустройства. Получи доступ к самым мощным программам с огромной скидкой ----https://live.skillbox.ru/code/online/250619/special/

​The best laid plans

🔗 The best laid plans
Visualising Yemen’s Invisible War

​How to Develop a 1D Generative Adversarial Network From Scratch in Keras

Generative Adversarial Networks, or GANs for short, are a deep learning architecture for training powerful generator models. A generator model is capable of generating new artificial samples that plausibly could have come from an existing distribution of samples. GANs are comprised of both generator and discriminator models.

https://machinelearningmastery.com/how-to-develop-a-generative-adversarial-network-for-a-1-dimensional-function-from-scratch-in-keras/

🔗 How to Develop a 1D Generative Adversarial Network From Scratch in Keras
Generative Adversarial Networks, or GANs for short, are a deep learning architecture for training powerful generator models. A generator model is capable of generating new artificial samples that plausibly could have come from an existing distribution of samples. GANs are comprised of both generator and discriminator models. The generator is responsible for generating new samples …

​Machine Learning Engineer Nanodegree-
Official link to Udacity's Machine Learning Engineer Nanodegree

https://www.udacity.com/course/machine-learning-engineer-nanodegree--nd009t

🔗 Become a Machine Learning Engineer | Udacity
Build a solid foundation in Supervised, Unsupervised, Reinforcement, and Deep Learning. Then, use these skills to test and deploy machine learning models in a production environment.

​Basic Data Wrangling & Visualization with an ETF

🔗 Basic Data Wrangling & Visualization with an ETF
Overview

​New AI programming language goes beyond deep learning

https://news.mit.edu/2019/ai-programming-gen-0626

🔗 New AI programming language goes beyond deep learning
General-purpose language works for computer vision, robotics, statistics, and more.

​Speech Recognition using Artificial Neural Network (ANN)

🔗 Speech Recognition using Artificial Neural Network (ANN)
Speech Recognition Speech is the way of communication between people. The speech recognition is a software invention which converts our spoken language into a machine-readable format. Nowadays speech recognition is useful for interaction between human and machines or mobile devices. So, it is ve

​List of Top blogs/Newsletter on Artificial Intelligence

Here are 15 machine learning, artificial intelligence, and deep learning blogs you should add to your reading lists

1. Machine Learning Mastery by Jason Brownlee
https://machinelearningmastery.com/about/

2. AI Trends
https://www.aitrends.com/

3. Algorithmia
https://blog.algorithmia.com/

4. AITopics (An official publication of the AAAI.)
https://aitopics.org/search

5. Open AI
https://openai.com/

6. MIT AI Blog
https://news.mit.edu/topic/artificial-intelligence2

7. DataRobot Blog
https://blog.datarobot.com/

8. Andreessen Horowitz
https://aiplaybook.a16z.com/docs/intro/getting-started

9. Chatbots Magazine (The #1 place to learn about chatbots.)
https://chatbotsmagazine.com/

10. Machine Intelligence Research Institute (MIRI)
https://intelligence.org/blog/

11. Chatbots Life
(Best Place to Learn About Bots)
https://chatbotslife.com/

12. 33 rd square
https://www.33rdsquare.com/

13. Artificial Intelligence Blogs
https://www.artificial-intelligence.blog/news/

14. Machine Learnings
https://machinelearnings.co/

15. C T Vision
https://ctovision.com//

🔗 Algorithmia Blog
Deploying AI at Scale

🎥 Deep Learning Applications | Deep Learning Applications In Real Life | Deep learning | Simplilearn
👁 1 раз ⏳ 775 сек.
This video on Deep Learning Applications covers the exciting areas and sectors of business that uses Deep Learning widely every day. We will see how Deep Learning is used in healthcare to improve people's life. We will understand how Amazon, Netflix use Deep Learning to provide better customer experience. We will learn to generate music, audio, and color images using Deep Learning. This video will also give us an idea of how Deep Learning is used in advertising and in predicting earthquakes. Now, let us jum

​Log Book — Practical guide to Linear & Polynomial Regression in R

🔗 Log Book — Practical guide to Linear & Polynomial Regression in R
This is a practical guide to linear and polynomial regression in R. I have tried to cover the basics of theory and practical…

​AI generating football video game commentary

🔗 AI generating football video game commentary
My approach to generating dynamic commentary in real time for Google’s football environment using GPT-2 language model.

🎥 Machine Learning Career Transition
👁 1 раз ⏳ 3323 сек.
Making a transition into Machine Learning is a journey paved with obstacles and learning. There is so much to learn and implement! This can get especially challenging if you’re coming from a non-technical background. But isn’t that the great thing about learning? We get to experiment with concepts, apply them in a safe academic environment, and add to our knowledge through practical applications. The experience becomes even richer when you’ve worked in the corporate field for a number of years. The best way

​Generalization Bounds: rely on your Deep Learning models

🔗 Generalization Bounds: rely on your Deep Learning models
How will your Deep Learning system perform on new data (generalize)? How bad can its performance get? Estimating the ability of an…