Hallucinogenic Deep Reinforcement Learning Using Python and Keras

https://goo.gl/MH9PPP

https://t.iss.one/ArtificialIntelligenceArticles

Spectral Inference Networks: Unifying Spectral Methods With Deep Learning

https://arxiv.org/abs/1806.02215 @ArtificialIntelligenceArticles

Workspaces on FloydHub : a new cloud IDE for deep learning

https://blog.floydhub.com/workspaces/ @ArtificialIntelligenceArticles

Soccer and Machine Learning

https://goo.gl/UPCzWD

https://t.iss.one/ArtificialIntelligenceArticles

This article is a comprehensive overview of using deep learning based object detection methods for aerial imagery via drones https://goo.gl/s1TSND @ArtificialIntelligenceArticles

Stochastic Weight Averaging — a New Way to Get State of the Art Results in Deep Learning

https://goo.gl/SyXMDX

https://t.iss.one/ArtificialIntelligenceArticles

Great talk from Andrej Karpathy about the challenges of building the Software 2.0 stack.

https://goo.gl/XxyZm1

https://t.iss.one/ArtificialIntelligenceArticles

Machine Learning Top 10 Articles for the Past Month (v.June 2018)

❄️💦10 مقاله برتر یادگیری ماشین به انتخاب Mybridge در ماه گذشته

https://goo.gl/yTVtv1 @ArtificialIntelligenceArticles

Improving Language Understanding with Unsupervised Learning

Unsupervised pre-training + fine-tuning (NLP)

By Alec Radford : https://blog.openai.com/language-unsupervised/

https://t.iss.one/ArtificialIntelligenceArticles

Yann LeCun :

ConvNet outperforms human dermatologists for melanoma detection.

Dermatologists in level-II protocol:
- sensitivity: 88.9% (±9.6%, P = 0.19)
- specificity: 75.7% (±11.7%, P < 0.05).

ConvNet:
- sensitivity: 88.9%
- specificity: 82.5%

"Conclusions: For the first time we compared a CNN’s diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians’ experience, they may benefit from assistance by a CNN’s image classification"

paper : https://goo.gl/oybrZj


https://t.iss.one/ArtificialIntelligenceArticles

پژوهشگران دانشگاه ام‌آی‌تی موفق شده‌اند با استفاده از هوش مصنوعی و امواج فرکانس رادیویی حرکات فیزیکی انسان رو از پشت دیوار تشخیص دهند

Artificial intelligence senses people through walls


Wireless smart-home system from the Computer Science and Artificial Intelligence Laboratory could monitor diseases and help the elderly “age in place.”

https://news.mit.edu/2018/artificial-intelligence-senses-people-through-walls-0612


paper: https://openaccess.thecvf.com/content_cvpr_2018/CameraReady/2406.pdf

https://t.iss.one/ArtificialIntelligenceArticles

AI can now generate memes

Abel L Peirson V & E Meltem Tolunay:
Dank Learning. Generating Memes Using Deep Neural Networks

https://arxiv.org/abs/1806.04510 @ArtificialIntelligenceArticles

Self-supervisory Signals for Object Discovery and Detection. https://arxiv.org/abs/1806.03370 @ArtificialIntelligenceArticles

Altered Fingerprints: Detection and Localization

Achieves a True Detection Rate (TDR) of 99.24% at a False Detection Rate (FDR) of 2%, outperforming published results

https://arxiv.org/abs/1805.0091

AI could get 100 times more energy-efficient with IBM’s new artificial synapses
Copying the features of a neural network in silicon might make machine learning more usable on small devices like smartphones.

https://goo.gl/hFfg69

paper : https://goo.gl/xyXbWo

https://t.iss.one/ArtificialIntelligenceArticles

مقاله جدیدی از پروفسور Li Fei-Fei
new paper : Li Fei-Fei
Learning to Decompose and Disentangle Representations for Video Prediction. https://arxiv.org/abs/1806.04166 @ArtificialIntelligenceArticles

vulnerabilities in #deeplearning could lead to new kinds of healthcare fraud and other issues https://goo.gl/JBktiY @ArtificialIntelligenceArticles

Generating NES music using deep learning

Code : https://github.com/chrisdonahue/nesmdb
Paper: https://arxiv.org/abs/1806.04278 @ArtificialIntelligenceArticles

AI Winter Is Well On Its Way
https://goo.gl/WCgwrh @ArtificialIntelligenceArticles

A nice review article about relational reasoning, relational inductive biases in typical deep learning building blocks, and graph networks. https://arxiv.org/abs/1806.01261 @ArtificialIntelligenceA

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution": Judea Pearl presents seven tasks which he claims are beyond reach of current machine learning systems but have been accomplished using the tools of causal modeling.

https://arxiv.org/abs/1801.04016

https://t.iss.one/ArtificialIntelligenceArticles