Philips Jobs - Research Scientist (m/f) Machine Learning / Medical Systems & Solutions in Hamburg... http://bit.ly/2vuP3eN #ai #ml #dl

Clever Camera App Uses Deep Learning to Perfectly Retouch Your Photos Before You Take Them http://news.mit.edu/2017/automatic-image-retouching-phone-0802 #ai #ml #dl

مجموعه ای از مقالات جالب #یادگیری_ماشین اخیرا در Arxiv منتشر شده

Collection of interesting #ML papers recently out on Arxiv

1️⃣DeSIGN: Design Inspiration from Generative Networks:
http://goo.gl/8GxWne
2️⃣FLIPDIAL: A Generative Model for Two-Way Visual Dialogue:
http://goo.gl/YSxcC3
3️⃣Training VAEs Under Structured Residuals:
http://goo.gl/kUdN1y

4️⃣Seeing Voices and Hearing Faces: Cross-modal biometric matching:
http://goo.gl/r4cBM5

5️⃣DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks:
http://goo.gl/dDGzwx

https://t.me/ArtificialIntelligenceArticles

6️⃣Deep Texture Manifold for Ground Terrain Recognition:
http://goo.gl/bNt6mV

https://t.me/ArtificialIntelligenceArticles

Step Change Improvement in Molecular Property Prediction with PotentialNet

Paper on a significant improvement in ability to predict molecular properties in drug design. #ML algorithms are getting better and better than classical methods.

Link: https://medium.com/@pandelab/step-change-improvement-in-molecular-property-prediction-with-potentialnet-f431ffa32a2c

#drugsdesign #biolearning #healthcare

Representer Point Selection for Explaining Deep Neural Networks by Joon Sik Kim & Chih-Kuan Yeh, #mldcmu

Why did a Deep Neural Network #DNN make a certain prediction

Learn more: https://blog.ml.cmu.edu/2019/04/19/representer-point-selection-explain-dnn/

#AI #machinelearning #deeplearning #ML

The field of #machinelearning seeks to answer the question "How can we build computer systems that automatically improve with experience, and what are the fundamental laws that govern all learning processes?," Tom Mitchell on the Discipline of Machine Learning

Story: https://mld.ai/6b76a
Paper: http://www.cs.cmu.edu/~tom/pubs/MachineLearning.pdf

#ML #artificialintelligence #research #carnegiemellon #scsatcmu [ machine learning ] [ artificial intelligence ] #AI #education

Machine Learning for Everyone.

The best general intro post about Machine Learning, covering everything you need to know not to get overxcited about SkyNet and to get general understanding of all #ML / #AI hype. You can surely save this post into «Saved messages» and forward it to your friends to make them familiar with the subject

Link: https://vas3k.com/blog/machine_learning/

#entrylevel #novice #general

A Recipe for Training Neural Networks by Andrej Karpathy

New article written by Andrej Karpathy distilling a bunch of useful heuristics for training neural nets. The post is full of real-world knowledge and how-to details that are not taught in books and often take endless hours to learn the hard way.

Link: https://karpathy.github.io/2019/04/25/recipe/

#tipsandtricks #karpathy #tutorial #nn #ml #dl

New Frontiers of Automated Mechanism Design for Pricing and Auctions by Maria-Florina Balcan, @mldcmu, Tuomas Sandholm, Ellen Vitercik @csdatcmu

Learn more → https://mld.ai/y1m
Tutorial Video Part I: https://youtu.be/buK3KXZcGAI
Tutorial Video Part II: https://youtu.be/T8gaK4Yw4zI

#MechanismDesign #GameTheory #Tutorial #MachineLearning #Optimization #ML

Must follow Github Repository
⚡️Contains +100 AI Cheatsheets
⚡️List of Free AI Courses
⚡️Free Online Books
⚡️Top 10 Online Books
⚡️Research Papers with codes
⚡️Top Videos&Lecture on AI+ML
⚡️+99 AI Researchers
⚡️Top website which should follow
⚡️+121 Free Datasets
⚡️+53 AI Framework and many more
All in one Github Repository
https://github.com/Niraj-Lunavat/Artificial-Intelligence
#Github #artificialIntellige­nce #ai #ml #machinelearning

Carnegie Mellon University, Accepted Papers at NeurIPS 2019

Learn more → https://mld.ai/neurips2019

#NeurIPS2019 #NeurIPS #MachineLearning #ML #ComputationalNeuroscience #Research #CarnegieMellon #CMUAI #mldcmu

Even young children when they look at a picture, not only identify objects such as "cat," "book," "chair." but also narrate the context and probably caption them. Now, computers are getting smart enough to do that too. In this TED talk, computer vision expert Fei-Fei Li describes the state of the art — including the database of 15 million photos her team built to "teach" a computer to understand pictures — and the key insights yet to come.#alintelligence #deeplearning #datascience #machinelearning #ML #Algorithm #Python #R #professional #industry #bigdata #ai #community #workforce

https://www.youtube.com/watch?v=40riCqvRoMs

Amazing work on generative adversarial networks by Tero Karras, Samuli Laine and Timo Aila of NVIDIA. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. #education #professionals #careers #artificialintelligence #deeplearning #datascience #machinelearning #ML #Algorithm #Python #R #professional #industry #bigdata #ai #community #workforce

The research paper is available : http://stylegan.xyz/paper

Video link : https://www.youtube.com/watch?v=kSLJriaOumA

We just released our #NeurIPS2019 Multimodal Model-Agnostic Meta-Learning (MMAML) code for learning few-shot image classification, which extends MAML to multimodal task distributions (e.g. learning from multiple datasets). The code contains #PyTorch implementations of our model and two baselines (MAML and Multi-MAML) as well as the scripts to evaluate these models to five popular few-shot learning datasets: Omniglot, Mini-ImageNet, FC100 (CIFAR100), CUB-200-2011, and FGVC-Aircraft.

Code: https://github.com/shaohua0116/MMAML-Classification

Paper: https://arxiv.org/abs/1910.13616

#NeurIPS #MachineLearning #ML #code

What is adversarial machine learning, and how is it used today?

-Generative modeling, security, model-based optimization, neuroscience, fairness, and more!

Here's a fantastic video overview by Ian Goodfellow.
http://videos.re-work.co/videos/1351-ian-goodfellow
#ML #adversarialML #AI #datascience

MIT's 1-week deep learning bootcamp is available online for free.

Check out the intro talk here:https://www.youtube.com/watch?v=5v1JnYv_yWs&fbclid=IwAR3bSAJGZzf04z1BnREJMpZsX6IUVcFtHfoolgh-apLwKXhPBMTAySAF9Rk
#DeepLearning #ML #MachineLearning #RL #DL

Overcoming Mode Collapse and the Curse of Dimensionality by Ke Li, Ph.D.

Talk → https://youtu.be/v9GfcBwtOaw
Slides → https://mld.ai/m8xc

#modecollapse #machinelearning #ml #dimensionality #ResearchPapers

ข้อมูลวีดีโอ หาก Model รู้เข้าใจระดับความลึกและรูปทรงจะสามารถ ทำ Augmented เติมเข้าไปในวีดีโอได้อย่างน่าสนใจ

https://www.youtube.com/watch?v=51CQObCd_K0&feature=youtu.be&fbclid=IwAR3UHcxiphy2OnhHpcKZSf4zYB-nW8PHyPHBgxcltw-8SCpi8z0sQ8mGtaw

​​CREME – python library for online ML

All the tools in the library can be updated with a single observation at a time, and can therefore be used to learn from streaming data.

The model learns from one observation at a time, and can therefore be updated on the fly. This allows to learn from massive datasets that don't fit in main memory. Online machine learning also integrates nicely in cases where new data is constantly arriving. It shines in many use cases, such as time series forecasting, spam filtering, recommender systems, CTR prediction, and IoT applications. If you're bored with retraining models and want to instead build dynamic models, then online machine learning might be what you're looking for.

Here are some benefits of using creme (and online machine learning in general):
• incremental – models can update themselves in real-time
• adaptive – models can adapt to concept drift
• production-ready – working with data streams makes it simple to replicate production scenarios during model development
• efficient – models don't have to be retrained and require little compute power, which lowers their carbon footprint


api reference: https://creme-ml.github.io/content/api.html
github: https://github.com/creme-ml/creme

#ml #online #learning

Enzyme, a compiler plug-in for importing foreign code into systems like TensorFlow & PyTorch without having to rewrite it. v/@MIT_CSAIL

Paper: http://bit.ly/EnzymePDF

More: http://bit.ly/EnzymeML

#ML #MachineLearning #PyTorch #TensorFlowJS #NeurIPS #tensorflow #AI