​​#Infographic : 8 ways AI is Transforming #healthcare

Application of #StyleGAN: site, which generates new people every page refresh.

Link: https://thispersondoesnotexist.com

OpenAI’s new model can generate surprisingly realistic fake news.

New model, called GPT-2 is an unsupervised language model that can generate coherent paragraphs and perform rudimentary reading comprehension, machine translation, question answering, and summarization — all without task-specific training.

Link: https://blog.openai.com/better-language-models/
Paper: https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf

#OpenAI #NLP #fakenews #qa #DL

One of the most complete lists of #NN types.

Link: http://www.asimovinstitute.org/neural-network-zoo/

​​Object Detection Networks and Augmented Reality for Cellular Detection in Fluorescence Microscopy Acquisition and Analysis.

#DL automated microscopy with objection detection.

Paper: https://www.biorxiv.org/content/10.1101/544833v1

#AugmentedReality

​​SC-FEGAN: Face Editing Generative Adversarial Network with User’s Sketch and Color

New paper on architecture that lets you add/change: earrings, glasses, hair style, dimples, & more. Sketches are trasformed to the photo by #GAN network.

ArXiV: https://arxiv.org/pdf/1902.06838.pdf
Code: https://github.com/JoYoungjoo/SC-FEGAN

"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet"

A "bag of words" of nets on tiny 17x17 patches suffice to reach AlexNet-level performance on ImageNet. A lot of the information is very local.

Paper: https://openreview.net/forum?id=SkfMWhAqYQ

#fun #CNN #CV #ImageNet

Probabilistic foundations of econometrica: part 1

Great intro into #statistics basics.

Link: https://freakonometrics.hypotheses.org/57649

#beginner #novice #entrylevel

Analyzing Experiment Outcomes: Beyond Average Treatment Effects

Good #statistics article on why tail distribution and #experimentdesign matters. Quantile treatment effects (QTEs) helps to capture the inherent heterogeneity in treatment effects when riders and drivers interact within the #Uber marketplace.

Link: https://eng.uber.com/analyzing-experiment-outcomes/

​​Pseudo-extended Markov chain Monte Carlo

Pseudo-Extended #MC for easier sampling from multimodal posteriors. Extend the target distribution and then run your favourite sampler (f.e. #HMC).

ArXiV: https://arxiv.org/abs/1708.05239

#statistics

​​Weakly supervised mitosis detection in breast histopathology images using concentric loss

Weakly-supervised mitosis detection in breast histopathology images shows that only using one-click annotation can obtain the best performances on three challenging datasets.

Link: https://www.sciencedirect.com/science/article/abs/pii/S1361841519300118?dgcid=author

#healthcare #medical #CV #cancer #DL

​​Learning to Generalize from Sparse and Underspecified Rewards

Applying reinforcement learning to environments with sparse and underspecified rewards is an ongoing challenge, requiring generalization from limited feedback. Novel method that provides more refined feedback to the agent.

Link: https://ai.googleblog.com/2019/02/learning-to-generalize-from-sparse-and.html

#Google #RL

​​🔥The Blowjob Paper: Scientists Processed 109 Hours of Oral Sex to Develop an AI that Sucks Dick

Running a channel about AI, one can not miss the attempt to apply machine learning to calibrate sex toys performance. That’s what researchers did, trying to improve Autoblow 2 device characteristics.

Link: https://motherboard.vice.com/en_us/article/pa9nvv/the-blowjob-paper-scientists-processed-109-hours-of-oral-sex-to-develop-an-ai-that-sucks-dick-autoblow
Paper: https://www.autoblow.com/bjpaper/

#ML #DL #AIeverywhere

​​Food Discovery with Uber Eats: Recommending for the Marketplace

Another great article from #Uber engeneering team on how they built recommendation engine for #UberEats and what balance they had to maintain.

Link: https://eng.uber.com/uber-eats-recommending-marketplace/

Lingvo: A TensorFlow Framework for Sequence Modeling

Release from #GoogleAI: general #tensorflow framework for #NLP.

#Lingvo is a deep learning framework used for sequence modeling tasks like machine translation, speech recognition, and speech synthesis.

Link: https://medium.com/tensorflow/lingvo-a-tensorflow-framework-for-sequence-modeling-8b1d6ffba5bb
Github: https://github.com/tensorflow/lingvo

​​How 20th Century Fox uses ML to predict a movie audience

All modern blockbusters seem the same. They have common patterns of more exciting periods following less exciting, rotating emotional moments with action period. It is more about following well-known structure and template to make a well-boxing movie, than about director’s skill. No suprise, that #ML can be used to predict success of the movie by its trailer.

Link: https://cloud.google.com/blog/products/ai-machine-learning/how-20th-century-fox-uses-ml-to-predict-a-movie-audience

#DL #LAindustry #Google

🇫🇷From the subscribers living (or being) in Paris:

Tomorrow, Saturday, 2nd of March, in Paris, come to DS Breakfast at 10h30 at Malongo Cafe, 50 Rue Saint-André des Arts, 75006 Paris.

​​Deep Reinforcement Learning for de-novo Drug Design

- 2 networks trained separately:
- generative produces chemically feasible molecule reps
- predictive forecasts desired properties.
- then both trained jointly with the #RL

Link: https://github.com/isayev/ReLeaSE

#PyTorch

#StyleGAN trained on art perfomance.

#GAN