Tensor flow. Smooth dive

https://www.youtube.com/watch?v=cs9dBQxe8yM

🎥 Meetup #17. Tensor flow. Smooth dive
👁 8 раз ⏳ 3742 сек.
Видео доклада с семнадцатой встречи сообщества .Nuts. C докладом выступил Сергей Лозовской. Доклад состоялся 28 февраля 2019 года.

​Machine Learning
A Probabilistic Perspective
Kevin P. Murphy

📝 Machine-Learning-A-Probabilistic-Perspective.pdf - 💾26 293 504

🎥 Introduction to Deep Learning Lecture 14
👁 1 раз ⏳ 4422 сек.

Similarity learning using deep neural networks - Jacek Komorowski

Наш телеграм канал - https://tele.click/ai_machinelearning_big_data

https://www.youtube.com/watch?v=OkcS4qE4Zsg

🎥 Similarity learning using deep neural networks - Jacek Komorowski
👁 1 раз ⏳ 2116 сек.
PyData Warsaw 2018

Deep neural network give very good results in visual object recognition tasks, but they require large number of training examples from each category. I'll present a class of neural network architectures, that can be used when only few training examples from each class are available. They are based on 'similarity learning' concept and can be used to solve various practical problems.
===
www.pydata.org

PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the

​3 Levels of Deep Learning Competence

https://machinelearningmastery.com/deep-learning-competence/

🔗 3 Levels of Deep Learning Competence
Deep learning is not a magic bullet, but the techniques have shown to be highly effective in a large number of very challenging problem domains. This means that there is a ton of demand by businesses for effective deep learning practitioners. The problem is, how can the average business differentiate between good and bad practitioners? …

​Tutorial wineural differentiation
https://nbviewer.jupyter.org/github/urtrial/neural_ode/blob/master/Neural%20ODEs.ipynb

🔗 Notebook on nbviewer
Check out this Jupyter notebook!

​Learning Theory: Empirical Risk Minimization

https://towardsdatascience.com/learning-theory-empirical-risk-minimization-d3573f90ff77?source=collection_home---4------1---------------------

🔗 Learning Theory: Empirical Risk Minimization – Towards Data Science
Delving into ERM, one of the essential neglected concepts in machine learning

Practical Deep Learning For Coders 2018
https://www.youtube.com/watch?v=IPBSB1HLNLo&list=PLfYUBJiXbdtS2UQRzyrxmyVHoGW0gmLSM&index=2&t=0s

https://www.youtube.com/playlist?list=PLfYUBJiXbdtS2UQRzyrxmyVHoGW0gmLSM

🎥 Lesson 1: Deep Learning 2018
👁 133 раз ⏳ 5195 сек.
NB: Please go to http://course.fast.ai to view this video since there is important updated information there. If you have questions, use the forums at http://forums.fast.ai

Welcome to the start of your fast.ai journey! In today’s lesson you’ll set up your deep learning server, and training your first image classification model (a convolutional neural network, or CNN), which will learn to distinguish dogs from cats nearly perfectly. If you need help at any time, head over to forums.fast.ai where over a thou

🎥 Artificial Intelligence And Machine Learning E-Degree : Sneak Peak | Eduonix
👁 2 раз ⏳ 2819 сек.
Machine Learning is one of the technologies which gained immense popularity recently. This video gives a sneak peek of our AI and ML E-Degree campaign on Kickstarter. Herein, the tutor explains the different models of machine learning such as supervised, unsupervised and reinforcement ML models along with the insights into data science workflows and deep learning.

If you are one of those who is always intrigued by the concepts of AI and ML, then you can learn it from the very beginning by backing our AI a

🎥 Distributed deep learning and why you may not need it - Jakub Sanojca, Mikuláš Zelinka
👁 5 раз ⏳ 1729 сек.
PyData Warsaw 2018

Deep learning thrives with always bigger networks and always growing datasets but single machine can only handle so much. When to scale to multiple machines and how do do it efficiently? What pros and cons available options have and what is theory behind their approach to distributed training? In this talk we will answer those questions and show what problems we are trying to solve at Avast.
===
www.pydata.org

PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organizat

🎥 Keynote: The Neural Aesthetic - Gene Kogan
👁 1 раз ⏳ 2861 сек.
PyData Warsaw 2018

Over the past several years, two trends in machine learning have converged to pique the curiosity of artists working with code: the proliferation of powerful open source deep learning frameworks like TensorFlow and Torch, and the emergence of data-intensive generative models for hallucinating images, sounds, and text as though they came from the oeuvre of Shakespeare, Picasso, or just a gigantic database of digitized cats.
===
www.pydata.org

PyData is an educational program of NumFOCUS,

🎥 Introduction to Deep Learning Lecture 15
👁 1 раз ⏳ 4560 сек.

🎥 Deep Learning на пальцах 3 - Нейронные сети
👁 1 раз ⏳ 5545 сек.
Курс: http://dlcourse.ai
Слайды: https://www.dropbox.com/s/r2zac25mur1g16z/Lecture%203%20-%20Neural%20Networks%20-%20annotated.pptx?dl=0
Лекции каждую неделю в среду 8:40 утра по Мск, 12:40 по Нск.
9:40 вечера вторника по PST.

​Exploring Neural Networks with Activation Atlases

Наш телеграм канал - https://tele.click/ai_machinelearning_big_data

https://ai.googleblog.com/2019/03/exploring-neural-networks.html

🔗 Exploring Neural Networks with Activation Atlases
Posted by Shan Carter, Software Engineer, Google AI Neural networks have become the de facto standard for image-related tasks in computin...

Серия докладов по машинному обучению

Наш телеграм канал - https://tele.click/ai_machinelearning_big_data

1. Neural Networks For Recommender Systems
2. 7 Steps Of Machine Learning
3. Blockchain + AI = Decentralized Artificial Intelligence
4. Predicting Titanic Survivors With #MachineLearning
5. Natural Language Processing @ FACEBOOK Scale
6. [Machine Learning] Is It Food? A Journey Of Minds, Machines And Meals
7. On-device Machine Learning With #TensorFlow
8. Deep Learning with #Go
9. Deep Learning For Developers
10. The Fastest Path To #DeepLearning

🎥 Neural Networks For Recommender Systems
👁 92 раз ⏳ 1247 сек.
Recommender Systems are arguably the most common business application of Machine Learning systems. Recently a new blend of recommender systems have...

🎥 7 Steps Of Machine Learning
👁 49 раз ⏳ 2890 сек.
From detecting skin cancer, to sorting cucumbers, to detecting escalators in need of repairs, machine learning has granted computer systems entirel...

🎥 Blockchain + AI = Decentralized Artificial Intelligence
👁 49 раз ⏳ 731 сек.
What happens when we take two hottest technologies of today, AI and Blockchain, and put them together? Watch this talk by Siraj Raval to get the an...

🎥 Predicting Titanic Survivors With Machine Learning
👁 25 раз ⏳ 3070 сек.
What's a better way to understand machine learning than a practical example? And who hasn't watched the classic 1997 movie? In this session, we wil...

🎥 Natural Language Processing @ FACEBOOK Scale
👁 2 раз ⏳ 1111 сек.
At Facebook, text understanding is the key to surfacing content that’s relevant and personalized, plus enabling new experiences like social recomme...

🎥 [Machine Learning] Is It Food? A Journey Of Minds, Machines And Meals
👁 1 раз ⏳ 1976 сек.
Machine Learning is no longer just an academic study. Tools like Tensorflow have opened new doorways in the world of application development. Learn...

🎥 On-device Machine Learning With TensorFlow
👁 24 раз ⏳ 1084 сек.
Machine learning has traditionally been the solely performed on servers and high performance machines. But there is great value is having on-device...

🎥 Deep Learning with Go
👁 65 раз ⏳ 2986 сек.
You’ve heard about self-driving cars, self-organizing drone swarms, conversational interfaces, and emotion recognition. That’s all ‘deep learning’ ...

🎥 Deep Learning For Developers
👁 5 раз ⏳ 2613 сек.
Deep Learning has taken the world of Computer Science by storm yet for many of us it remains an elusive sci-fi-like buzzword. After years of featur...

🎥 The Fastest Path To Deep Learning
👁 3 раз ⏳ 1929 сек.
Learning Deep Learning can be confusing and often very frustrating. In this talk, Sam will set out a roadmap to go from knowing nothing to being fl...

​ИИ, обученный на основе результатов десятилетий кулинарных экспериментов, создает новые блюда
Искусственный интеллект (слабая его форма) проникает в науку, искусство, военное дело, игры и многие другие сферы. Сейчас эта технология начинает применяться и в такой неожиданной отрасли, как кулинария. Пионером стала компания IBM, которая воспользовалась возможностями Watson для составления новых рецептов и улучшения уже существующих.

Эксперты, которые работают над проектом, считают, что если тестовая фаза эксперимента пройдет хорошо, то ИИ окажет значительное влияние на то, что мы едим каждый день. До идеала еще очень далеко, но кое-какие успехи уже есть.
https://habr.com/ru/company/madrobots/blog/442866/

🔗 ИИ, обученный на основе результатов десятилетий кулинарных экспериментов, создает новые блюда
Искусственный интеллект (слабая его форма) проникает в науку, искусство, военное дело, игры и многие другие сферы. Сейчас эта технология начинает применяться и...

TensorFlow Probability: Learning with confidence (TF Dev Summit '19)

Наш телеграм канал - https://tele.click/ai_machinelearning_big_data

https://www.youtube.com/watch?v=BrwKURU-wpk

🎥 TensorFlow Probability: Learning with confidence (TF Dev Summit '19)
👁 1 раз ⏳ 837 сек.
TensorFlow Probability (TFP) is a Python library built on TensorFlow that makes it easy to combine probabilistic models and deep learning on modern hardware (TPU, GPU). It's for data scientists, statisticians, and ML researchers/practitioners who want to encode domain knowledge to understand data and make predictions with uncertainty estimates. In this talk we focus on the "layers" module and demonstrate how TFP "distributions" fit naturally with Keras to enable estimating aleatoric and/or epistemic uncerta

Машинное обучение . SVM, PCA.
Наш телеграм канал - https://tele.click/ai_machinelearning_big_data

https://www.youtube.com/watch?v=nF0rqbOwOAw

🎥 Машинное обучение 4. SVM, PCA.
👁 1 раз ⏳ 3812 сек.
Лекция от 5 февраля 2019.
Лектор: Владислав Гончаренко

Снимал: Михаил Кревский
Монтировал: Александр Гришутин

🎥 Get more out of Remedy with Machine Learning, AI and Automation updated
👁 1 раз ⏳ 2703 сек.
Watch webinar to know
What is AI, Machine Learning and NLP in the context of Service Desk
How Service Desk burden can be reduced by using cognitive capabilities?
How end user experience can change with intelligent service desk and automation?

🎥 Deep Learning, Vision and Speech - an update from the trenches, Chris Rowen, Samsung Forum
👁 1 раз ⏳ 3203 сек.
Spectacular successes by deep learning platforms in computer vision, speech and other pattern recognition tasks are capturing the attention of software developers and system architects across many applications. In this talk, Chris Rowen outlines the key ideas of deep learning, explores the systematic improvements in accuracy in perception and recognition tasks, and looks at the rapid changes in underlying computer architectures, in application development methods, and in human-machine interfaces.

Two exam