People should stop training radiologists now. It is just completely obvious within 5 years deep learning is going to do better than radiologists."

-- Geoffrey Hinton

https://www.youtube.com/watch?v=2HMPRXstSvQ&feature=youtu.be&t=29

Sequential Convolutional Recurrent Neural Networks for Fast Automatic Modulation Classifi... https://arxiv.org/abs/1909.03050

Using Machine Learning to Battle Antibiotic Resistance
https://www.the-scientist.com/lab-tools/using-machine-learning-to-battle-antibiotic-resistance-65785

Intel AI Developer Program (Free)

https://software.intel.com/en-us/ai/courses

Find The Most Updated and Free Artificial Intelligence, Machine Learning, Data Science, Deep Learning, Mathematics, Python, R Programming Resources.
https://www.marktechpost.com/free-resources/

Deep weakly-supervised learning methods for classification and localization in histology images: a survey
Rony et al.: https://arxiv.org/abs/1909.03354
#ArtificialIntelligence #DeepLearning #MachineLearning

📝 The paper: Adversarial Examples Are Not Bugs, They Are Features

video: https://www.youtube.com/watch?v=AOZw1tgD8dA

available here: https://gradientscience.org/adv/

article: https://distill.pub/2019/advex-bugs-discussion/

SpeechBrain
A PyTorch-based Speech Toolkit : https://speechbrain.github.io
Project Leader: Mirco Ravanelli
#Speech #PyTorch #SpeechBrain

Modern Perspectives on Reinforcement Learning in Finance
Petter Kolm and Gordon Ritter : https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3449401
#ReinforcementLearning #Finance #Hedging

List of institutions with most accepted papers at NeurIPS.
Github code for this graph : https://lnkd.in/edwhZMf
Medium Link: https://medium.com/@dcharrezt/neurips-2019-stats-c91346d31c8f

Understanding Transfer Learning for Medical Imaging

ArXiV: https://arxiv.org/abs/1902.07208

#biolearning #dl #transferlearning

Productionizing NLP Models
https://towardsdatascience.com/productionizing-nlp-models-9a2b8a0c7d14

Resources for Getting Started With Probability in Machine Learning
https://machinelearningmastery.com/probability-resources-for-machine-learning/

In fact, your deep learning paper is the all-time most important Nature paper when ranked with eigencentrality, surpassing the second place “small world” paper by Duncan Watts et al published in late 90’s. Atari is the third. We use eigencentrality because citation count can be gamed easily. https://academic.microsoft.com/search?q=nature&qe=%40%40%40Composite(J.JN%3D%3D%27nature%27)&f=&orderBy=0&skip=0&take=10

Interested in becoming a data scientist?⠀
⠀
These are the 10 most important machine learning algorithms that you need to master to break into the field:⠀
⠀
• Linear regression ⠀
• Logistic regression⠀
• SVM⠀
• Random forest⠀
• Gradient boosting⠀
• PCA⠀
• K-means clustering⠀
• Collaborative filtering⠀
• kNN⠀
• ARIMA⠀
⠀
Bonus: Neural networks⠀
⠀
⠀
And here are the course notes and book that I first used to learn machine learning:⠀

➡ https://l2r.cs.uiuc.edu/~danr/Teaching/CS446-17/lectures.html ⠀
➡
https://web.stanford.edu/~hastie/ElemStatLearn/printings/ESLII_print12.pdf

⠀
👆 These notes do an amazing job teaching the algorithms with deeper mathematical rigor while still being easy to follow.⠀
⠀
⠀
Master the above algorithms and you'll be well on your way to becoming a data scientist.⠀
⠀
#aspiring #datascientist #datascience #machinelearning #coding⠀
⠀
For more detailed info, make sure to join my mailing list - you'll love the tips I share to help you break into the field -> https://www.datasciencedreamjob.com/free-tips

Meta-Learning with Implicit Gradients
Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine : https://arxiv.org/abs/1909.04630
#MachineLearning #ArtificialIntelligence #Optimization #Control #MetaLearning

Batch Normalization is a Cause of Adversarial Vulnerability

Abstract - Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low training error. However, it also reduces robustness to small adversarial input perturbations and noise by double-digit percentages, as we show on five standard data-sets. Furthermore, substituting weight decay for batch norm is sufficient to nullify the relationship between adversarial vulnerability and the input dimension. Our work is consistent with a mean-field analysis that found that batch norm causes exploding gradients.

Page - https://arxiv.org/abs/1905.02161

PDF - https://arxiv.org/pdf/1905.02161.pdf

Machine Learning for Physics and the Physics of Learning Tutorials"
Videos and slides, by IPAM (an NSF Math Institute at UCLA dedicated to promoting the interaction of math with other disciplines):
https://www.ipam.ucla.edu/programs/workshops/machine-learning-for-physics-and-the-physics-of-learning-tutorials/?tab=schedule
https://t.iss.one/ArtificialIntelligenceArticles

#MLP2019 #MachineLearning #Physics