​Regularization for Neural Networks with Framingham Case Study

🔗 Regularization for Neural Networks with Framingham Case Study
L1, L2, elastic net, and group lasso regularization

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 ReFocus: Making Out-of-Focus Microscopy Images In-Focus Again
Microscopy images are widely used for the diagnosis of various diseases such as infections and cancers. Furthermore, they facilitate basic…

​#AI #ArtificialIntelligence #DeepLearning #MachineLearning
#CVPR2019 in one link. Enjoy woth up-to-date research papers and hot

https://openaccess.thecvf.com/content_CVPR_2019/html/

🔗 Index of /content_CVPR_2019/html

​Unsupervised Co-Learning on G-Manifolds Across Irreducible Representations

Authors: Yifeng Fan, Tingran Gao, Zhizhen Zhao

Abstract: We introduce a novel co-learning paradigm for manifolds naturally equipped with a group action

🔗 Unsupervised Co-Learning on $\mathcal{G}$-Manifolds Across Irreducible Representations
We introduce a novel co-learning paradigm for manifolds naturally equipped with a group action, motivated by recent developments on learning a manifold from attached fibre bundle structures. We utilize a representation theoretic mechanism that canonically associates multiple independent vector bundles over a common base manifold, which provides multiple views for the geometry of the underlying manifold. The consistency across these fibre bundles provide a common base for performing unsupervised manifold co-learning through the redundancy created artificially across irreducible representations of the transformation group. We demonstrate the efficacy of the proposed algorithmic paradigm through drastically improved robust nearest neighbor search and community detection on rotation-invariant cryo-electron microscopy image analysis.

​June Edition: Probability, Statistics & Machine Learning

🔗 June Edition: Probability, Statistics & Machine Learning
Everyone wants to be in the field of Data Science and Analytics as it’s challenging, fascinating as well as rewarding. You have to be…

​Kernel Secrets in Machine Learning

🔗 Kernel Secrets in Machine Learning
This post is not about deep learning. But it could be might as well. This is the power of kernels. They are universally applicable in any…

​Введение в свёрточные нейронные сети (Convolutional Neural Networks)

🔗 Введение в свёрточные нейронные сети (Convolutional Neural Networks)
Полный курс на русском языке можно найти по этой ссылке. Оригинальный курс на английском доступен по этой ссылке. Выход новых лекций запланирован каждые 2-3 дн...

🎥 Tensorflow Math Operations using Constants: Tensorflow Tutorial Series
👁 1 раз ⏳ 1497 сек.
Tensorflow Math Operations using Constants: Tensorflow Tutorial Series

Welcome to "The AI University".

Subtitles available in: Hindi, English, French

About this video:
This video explains explaining basic mathematical operation i.e. how to perform mathematical operations in Tensorflow. It also explains Directed Acyclic Graphs as well as setting up operations in tensorflow and how it works.

FOLLOW ME ON:
Twitter: https://twitter.com/theaiuniverse
Facebook : https://www.facebook.com/theaiuniv

​One-Shot Learning with Siamese Networks, Contrastive Loss, and Triplet Loss for Face Recognition

https://machinelearningmastery.com/one-shot-learning-with-siamese-networks-contrastive-and-triplet-loss-for-face-recognition/

🔗 One-Shot Learning with Siamese Networks, Contrastive Loss, and Triplet Loss for Face Recognition
One-shot learning is a classification task where one, or a few, examples are used to classify many new examples in the future. This characterizes tasks seen in the field of face recognition, such as face identification and face verification, where people must be classified correctly with different facial expressions, lighting conditions, accessories, and hairstyles given …

🎥 ML-7 Reinforcement Learning: from Foundations to State-of-the-Art
👁 1 раз ⏳ 1778 сек.
Dr. Daniel Urieli

​Strategies for Global Optimization

🔗 Strategies for Global Optimization
Local and global optimization is usually known and somewhat ignored once we leave high school calculus. For a quick review, take the cover…

​Collection of MIT courses about Machine Learning
https://deeplearning.mit.edu/

🔗 MIT Deep Learning
Courses on deep learning, deep reinforcement learning (deep RL), and artificial intelligence (AI) taught by Lex Fridman at MIT. Lectures, introductory tutorials, and TensorFlow code (GitHub) open to all.

​Cписок бесплатных Natural Language Processing курсов

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
1)Speech and Language Processing by Dan Jurafsky and James Martin
https://web.stanford.edu/~jurafsky/slp3/

2) Deep Learning for Natural Language Processing by Richard Socher (Stanford University)
https://m.youtube.com/playlist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6

3. Natural Language Processing (NLP) by Microsoft
https://www.edx.org/course/natural-language-processing-nlp-2

4. Andrew Ng’s course on Machine Learning
https://www.coursera.org/learn/machine-learning/home/welcome

5. The video lectures and resources for Stanford’s Natural Language Processing with Deep Learning
https://web.stanford.edu/class/cs224n/

https://m.youtube.com/playlist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6

6. Sequence Models for Time Series and Natural Language Processing
https://www.coursera.org/learn/sequence-models-tensorflow-gcp?ranMID=40328&ranEAID=SAyYsTvLiGQ&ranSiteID=SAyYsTvLiGQ-ACNikbtJvh2d5Evme5yZQA&siteID=SAyYsTvLiGQ-ACNikbtJvh2d5Evme5yZQA&utm_content=10&utm_medium=partners&utm_source=linkshare&utm_campaign=SAyYsTvLiGQ

7. Deep Natural Language Processing course offered in Hilary Term 2017 at the University of Oxford.
https://www.cs.ox.ac.uk/teaching/courses/2016-2017/dl/

8. Natural Language Processing Fundamentals in Python by Datacamp
https://www.datacamp.com/courses/natural-language-processing-fundamentals-in-python

9 Natural Language Processing by Higher School of Economics
https://www.coursera.org/learn/language-processing?

10 How to Build a Chatbot Without Coding by IBM
https://www.coursera.org/learn/building-ai-powered-chatbots

11. CS 388: Natural Language Processing by University of Texas
https://www.cs.utexas.edu/~mooney/cs388/
12. Natural Language Processing with Python
https://www.nltk.org/book/

13. CSEP 517: Natural Language Processing by University of Washington
https://courses.cs.washington.edu/courses/csep517/17sp/

14. Dan Jurafsky & Chris Manning: Natural Language Processing
https://m.youtube.com/playlist?list=PL8FFE3F391203C98C

15. NATURAL LANGUAGE PROCESSING by Carnegie Mellon University
https://demo.clab.cs.cmu.edu/NLP/

16. CS224n: Natural Language Processing with Deep Learning by Stanford University
https://web.stanford.edu/class/cs224n/

​Multi-Category Visual Complexity Dataset

https://github.com/esaraee/Savoias-Dataset/

🔗 esaraee/Savoias-Dataset
A visual complexity dataset across seven different categories, including Scenes, Advertisements, Visualization and infographics, Objects, Interior design, Art, and Suprematism for computer vision ...

​Мы приглашаем дата сайнтистов принять участие в первом хакатоне ML Art hack
Дата: 29 июня
Место: Люмьер Холл, Санкт-Петербург
Вам предстоит объединиться в команды с медиа-художниками и вместе создать искусство.
В программе воркшопы по ML и TouchDesigner, где медиа художникам расскажем про дата сайнс, а дата сайнтистам — про медиа искусство.
Крутые проекты покажем на самом большом в мире куполе Планетария №1.
Вступайте во встречу фб: https://www.facebook.com/events/413754499175895/
Чтобы принять участие заполните анкету:
https://forms.gle/TbPH2v8SEp7rQPhZ8

🔗 Machine Learning + media art hackathon
Event in Санкт-Петербург by Alex Groznykh and Misha Anoshenko on суббота, июня 29 20196 posts in the discussion.

​Как компьютеры научились потрясающе хорошо распознавать изображения

Сегодня я могу, допустим, открыть Google Photos, написать «пляж», и увидеть кучу своих фотографий с различных пляжей, которые я посетил за последнее десятилетие. И я никогда не подписывал свои фотографии – Google распознаёт на них пляжи на основе их содержания. Эта, казалось бы, скучная особенность основывается на технологии под названием «глубокая свёрточная нейросеть», позволяющая программам понимать изображения при помощи сложного способа, недоступного технологиям предыдущих поколений.

В последние годы исследователи обнаружили, что точность ПО становится лучше по мере того, как они создают всё более глубокие нейросети (НС) и обучают их на всё более крупных наборах данных. Это создало ненасытную потребность в вычислительных мощностях, и обогатило производителей GPU, таких, как Nvidia и AMD. В Google несколько лет назад разработали собственные специальные чипы для НС, а другие компании пытаются угнаться за ней.
https://habr.com/ru/post/455331/

🔗 Как компьютеры научились потрясающе хорошо распознавать изображения
Знаковая научная работа от 2012 года преобразовала область программного распознавания изображений Сегодня я могу, допустим, открыть Google Photos, написать «пл...

​Diving into Google’s Landmark Recognition Kaggle Competition

🔗 Diving into Google’s Landmark Recognition Kaggle Competition
This recent Google Landmark Recognition competition has severely strained my relationship with my internet service provider, my GPUs, and…

🎥 On the Role of Knowledge Graphs for the Adoption of Machine Learning Systems in Industry
👁 2 раз ⏳ 1214 сек.
Presented by Dr. Freddy Lecue, Chief Artificial Intelligence (AI) Scientist at CortAIx (Centre of Research & Technology in Artificial Intelligence eXpertise) at Thales.

https://sps.columbia.edu/executive-education/knowledge-graph-conference/faculty/freddy-lecue-cortaix

Despite a surge of innovation focusing on Machine Learning-based AI systems, major industries remain puzzled about its impact at scale. This is particularly valid in the context of critical systems, as the need of robustness, trust and, in p

​A Gentle Guide to Starting Your NLP Project with AllenNLP

🔗 A Gentle Guide to Starting Your NLP Project with AllenNLP
Say Goodbye to Your Messy Codes!

​Demystifying Startup Equity with Data Science

🔗 Demystifying Startup Equity with Data Science
What percentage of ownership do investors acquire at each financing stage?