Neural Networks | Нейронные сети

RVOS: End-to-End Recurrent Network for Video Object Segmentation

RVOS: End-to-End Recurrent Network for Video Object Segmentation
CVPR 2019
CODE
https://imatge-upc.github.io/rvos/

🔗 RVOS: End-to-End Recurrent Network for Video Object Segmentation
Description here

imatge-upc.github.io

Description here

34 views16:33

Why we've misunderstood the nature-nurture debate.

Pre-Debate Material
"Making the Mind"
Why we've misunderstood the nature-nurture debate.
GARY MARCUS : http://bostonreview.net/books-ideas/gary-marcus-making-mind
#AIDebate

🔗 Making the Mind
From the Archive: Why we've misunderstood the nature-nurture debate.

Boston Review

Making the Mind

33 views18:34

AWS re:Invent 2019: Leadership session: Machine learning (AIM218-L)

🎥 AWS re:Invent 2019: Leadership session: Machine learning (AIM218-L)
👁 1 раз ⏳ 3229 сек.

We are embarking on the golden age of machine learning. Many of the constraints that typically held back the application of machine learning in the real world are starting to disappear. AWS offers a significant breadth and depth of cloud services. In this leadership session, we explore the democratization of machine learning and how the growth of cloud services makes it easy for customers to move from idea to production with machine learning.

We are embarking on the golden age of machine learning. Many of the constraints that typically held back the application of machine learning in the real world are starting to disappear. AWS offers a significant breadth and depth of cloud services. In this…

33 views20:35

Sebastian Thrun: Flying Cars, Autonomous Vehicles, and Education | Lex Fridman Podcast #59

Sebastian Thrun: Flying Cars, Autonomous Vehicles, and Education | Artificial Intelligence Podcast

🔗 Sebastian Thrun: Flying Cars, Autonomous Vehicles, and Education | Artificial Intelligence Podcast
Sebastian Thrun is one of the greatest roboticists, computer scientists, and educators of our time. He led development of the autonomous vehicles at Stanford that won the 2005 DARPA Grand Challenge and placed second in the 2007 DARPA Urban Challenge. He then led the Google self-driving car program which launched the self-driving revolution. He taught the popular Stanford course on Artificial Intelligence in 2011 which was one of the first MOOCs. That experience led him to co-found Udacity, an online educati

YouTube

39 views22:36

The Agony and the Ecstasy of my First Open Source Contribution

🔗 The Agony and the Ecstasy of my First Open Source Contribution
My first open source contribution wasn’t all smooth sailing, but it sure was thoroughly rewarding

The Agony and the Ecstasy of my First Open Source Contribution

My first open source contribution wasn’t all smooth sailing, but it sure was thoroughly rewarding

34 views00:37

Using Convolutional Neural Networks to Generate Harmony

🔗 Using Convolutional Neural Networks to Generate Harmony
Explores the data representation and temporal resolution on subjective quality and the negative log-likelihood of generated notes.

Using Convolutional Neural Networks to Generate Harmony

Explores the data representation and temporal resolution on subjective quality and the negative log-likelihood of generated notes.

34 views02:38

The Private AI Bootcamp offered by Microsoft Research (MSR) focused on tutorials of building privacy-preserving machine learning services and applications with homomorphic encryption (HE). Around 30 PhD students were invited to gather at the Microsoft Research…

🎥 Microsoft SEAL
👁 1 раз ⏳ 4494 сек.

The Private AI Bootcamp offered by Microsoft Research (MSR) focused on tutorials of building privacy-preserving machine learning services and applications with homomorphic encryption (HE). Around 30 PhD students were invited to gather at the Microsoft Research Lab in Redmond on Dec 2nd – 4th, 2019. The program contents were specifically designed for training. Participants mastered the use of HE, the Microsoft SEAL library, and the methodology behind building privacy-preserving machine learning solutions. As

Microsoft SEAL

31 views04:39

ИИ, пытающийся избежать проблем, научился сложному поведению

ИИ, пытающийся избежать проблем, научился сложному поведению

В обучении с подкреплением (Reinforcement Learning) часто используется любопытство в качестве мотивации для ИИ. Заставляющее его искать новые ощущения и исследовать окружающий мир. Но жизнь полна неприятных сюрпризов. Можно упасть с обрыва и с точки зрения любопытства это всегда будут очень новые и интересные ощущения. Но явно не то, к чему надо стремиться.
Разработчики из Berkeley перевернули задачу для виртуального агента с ног на голову: главной мотивирующей силой сделали не любопытство, а наоборот — стремление всеми силами избегать любой новизны. Но "ничего не делать" оказалось сложнее, чем кажется. Будучи помещенным в постоянно меняющийся окружающий мир, ИИ пришлось обучиться сложному поведению, чтобы избегать новых ощущений.

🔗 ИИ, пытающийся избежать проблем, научился сложному поведению
В обучении с подкреплением (Reinforcement Learning) часто используется любопытство в качестве мотивации для ИИ. Заставляющее его искать новые ощущения и исследо...

Хабр

В обучении с подкреплением (Reinforcement Learning) часто используется любопытство в качестве мотивации для ИИ. Заставляющее его искать новые ощущения и исследовать окружающий мир. Но жизнь полна...

32 views06:40

Python code for Artificial Intelligence: Foundations of Computational Agents — D. L. Poole, A. K. Mackworth (en) 2018

📝 Python code for Artificial Intelligence (en).pdf - 💾1 062 018

43 views08:40

Python code for Artificial Intelligence (en).pdf

1 MB

73 views08:40

Online Courses - Learn Anything, On Your Schedule | Udemy

FREE udemy course

Master Python Complete Course
Python for Data Science and Machine Learning
https://www.udemy.com/course/master-python-complete-course/

🔗 Бесплатное учебное руководство по теме "Python" — Master Python Complete Course
Python for Data Science and Machine Learning - Бесплатный курс

Udemy

Udemy is an online learning and teaching marketplace with over 213,000 courses and 62 million students. Learn programming, marketing, data science and more.

51 views10:40

Прикладное машинное обучение 14. Сегментация изображений.

🎥 Прикладное машинное обучение 14. Сегментация изображений.
👁 1 раз ⏳ 3850 сек.

Лекция от 06.12.2019
Лектор: Владислав Гончаренко

Снимал: Михаил Кревский
Монтировал: Артём Сапожников

Лекция от 06.12.2019
Лектор: Владислав Гончаренко

Снимал: Михаил Кревский
Монтировал: Артём Сапожников

34 views12:40

Small analysis of ICLR submissions:
https://colab.research.google.com/drive/12uwh2wI8bsxgF69XxpYbmE7rhu7EJ6Rb

🔗 Google Colaboratory

Google

ICLR20data.ipynb

Colaboratory notebook

35 views14:40

Optimal Real-time Scheduling for Black Hole Imaging

🔗 Optimal Real-time Scheduling for Black Hole Imaging
How to coordinate 11 telescopes in order to observe the black hole?

Optimal Real-time Scheduling for Black Hole Imaging

How to coordinate 11 telescopes in order to observe the black hole?

38 views16:41

Idea Behind LIME and SHAP

🔗 Idea Behind LIME and SHAP
Intuition behind ML interpretation models

Idea Behind LIME and SHAP

Intuition behind ML interpretation models

41 views18:41

The book to really start you on Machine Learning

🔗 The book to really start you on Machine Learning
Take your Machine Learning knowledge to the next level

The book to start you on Machine Learning

Take your Machine Learning knowledge to the next level

36 views20:41