​Physicists have discovered what makes neural networks so extraordinarily powerful

🔗 Physicists have discovered what makes neural networks so extraordinarily powerful
Nobody understands why deep neural networks are so good at solving complex problems. Now physicists say the secret is buried in the laws of physics.

​PyText

- PyText https://github.com/facebookresearch/pytext from Facebook:
- TLDR - FastText meets PyTorch;
- Very similar to AllenNLP in nature;
- Will be useful if you can afford to write modules for their framework to solve 100 identical tasks (i.e. like Facebook with 200 languages);
- In itself - seems to be too high maintenance to use;

I will not use use it.

#nlp
#deep_learning

🔗 facebookresearch/pytext
A natural language modeling framework based on PyTorch - facebookresearch/pytext

What Is Data Science? | Data Science Tutorial For Beginners | Data Science Using R | Edureka

🎥 What Is Data Science? | Data Science Tutorial For Beginners | Data Science Using R | Edureka

🎥 Прикладное машинное обучение в электронной коммерции. Александр Сербул (1С-Битрикс)
👁 1 раз ⏳ 3154 сек.

Deep Learning and Hyper-Personalization
https://towardsdatascience.com/deep-learning-and-hyper-personalization-e0d2b1fcb86?source=collection_home---4------0---------------------

https://habr.com/company/ods/blog/431512/

Небольшое исследование свойств простой U-net, классической сверточной сети для сегментации

#machinelearning #neuralnets #deeplearning #машинноеобучение

Наш телеграмм канал - https://yangx.top/ai_machinelearning_big_data

Deep Learning and Hyper-Personalization
https://towardsdatascience.com/deep-learning-and-hyper-personalization-e0d2b1fcb86?source=collection_home---4------1---------------------

​Deep Learning: What is it good for? - Prof. Ankit Patel - Rice University

🔗 Deep Learning: What is it good for? - Prof. Ankit Patel - Rice University
"In this talk, we will introduce deep learning and review some of the key advances in the field focusing on current attempts at a theoretical understanding. ...

​Analyzing model improvements - Deep Learning in Halite AI competition p.7

🔗 Analyzing model improvements - Deep Learning in Halite AI competition p.7
Analyzing our neural network model's improvement from random, and then considering our next steps. Channel membership: https://www.youtube.com/channel/UCfzlC...

​A Bag of Tricks for Image Classification

1. Large batch size
2. Mini model-tweaks
3. Refined Training Methods
4. Transfer Learning
5. Fancy Data Augmentation
https://link.medium.com/fzJvIBfsJS

#CV #tipsandtricks

🔗

🎥 Практическое занятие по профилю «Большие данные и машинное обучение» | Олег Ивченко
👁 1 раз ⏳ 6420 сек.

​[1812.06855] Bayesian Optimization in AlphaGo

🔗 [1812.06855] Bayesian Optimization in AlphaGo

​New interesting paper in Super Resolution area https://arxiv.org/abs/1812.04240

🔗 [1812.04240] Unsupervised Degradation Learning for Single Image Super-Resolution

​Коллекция Deep learning курсов от MIT

https://deeplearning.mit.edu/

🔗 MIT Deep Learning
Lectures on deep learning, deep reinforcement learning, artificial intelligence, and autonomous vehicles by Lex Fridman at MIT.

t-SNE: The Bits that No One Learns
https://towardsdatascience.com/t-sne-the-bits-that-no-one-learns-40add9e1978e?source=collection_home---4------2---------------------

https://habr.com/company/toshibarus/blog/433544/

Топ-5 сфер применения систем распознавания объектов

#machinelearning #neuralnets #deeplearning #машинноеобучение

Наш телеграмм канал - https://yangx.top/ai_machinelearning_big_data

​Lecture 7 - Reinforcement Learning | Deep Learning on Computational Accelerators

🔗 Lecture 7 - Reinforcement Learning | Deep Learning on Computational Accelerators
Given by Prof. Alex Bronstein

​Share Your AXA Research | Dr. E Ferrante: Deep Learning and Image Registration | AXA Research Fund

🔗 Share Your AXA Research | Dr. E Ferrante: Deep Learning and Image Registration | AXA Research Fund
What if, instead of explaining to a computer how to solve a problem, you let it learn by itself? Deep learning methods offer tremendous opportunities for mac...

​"New astonishing results in face generation by PGGAN author. All these people never existed. No cherry-picking was done"
🔎 arxiv.org/abs/1812.04948
👤 @j_links
📉 @loss_function_porn

🔗

Automated machine learning: a different notion of deep
https://towardsdatascience.com/automated-machine-learning-a-different-notion-of-deep-e0f7e5c06fb2?source=collection_home---4------2---------------------

​afshinea/stanford-cs-229-machine-learning

🔗 afshinea/stanford-cs-229-machine-learning
VIP cheatsheets for Stanford's CS 229 Machine Learning - afshinea/stanford-cs-229-machine-learning