Neural Network Embeddings Explained

How deep learning can represent War and Peace as a vector

Easy to read #novice article about #embeddings. Basically — how to represent everything as a vector.

Link: https://towardsdatascience.com/neural-network-embeddings-explained-4d028e6f0526

Building a Recommendation System Using Neural Network Embeddings

And, putting theory to work: embeddings for recommendation system

Link: https://towardsdatascience.com/building-a-recommendation-system-using-neural-network-embeddings-1ef92e5c80c9

Test-Driven Data Analysis

TDD is an approach to software development, suggesting that tests are essential part of the process. Over the years TDD have shown that it is required to maintain a good code base and the most common requirement for the lasting project.

Test driven approach can be maintain with data analysis too, with the reproducible research approach or TDDA, which is suggested by the latter link.

Link: http://www.tdda.info

#tdda

Unsupervised Machine Learning of Open Source Russian Twitter Data Reveals Global Scope and Operational Characteristics

Article on previously not found Russian Troll group on twitter.

Link: https://www.technologyreview.com/s/612252/data-mining-has-revealed-previously-unknown-russian-twitter-troll-campaigns/
ArXiV: https://arxiv.org/abs/1810.01466

#clustering #nlp #twitter

Digging into Airbnb data: reviews sentiments, superhosts, and prices prediction (part1)


Example of #AirBnB data research

Link: https://towardsdatascience.com/digging-into-airbnb-data-reviews-sentiments-superhosts-and-prices-prediction-part1-6c80ccb26c6a

Getting Started with Markov Decision Processes: Reinforcement Learning

Part 2: Explaining the concepts of the Markov Decision Process, Bellman Equation and Policies


Link: https://towardsdatascience.com/getting-started-with-markov-decision-processes-reinforcement-learning-ada7b4572ffb

#rl #reinforcementlearning #markovprocess

The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care

Interesting work looking at how AI could suggest optimal treatment for sepsis. Sepsis is a life threatening complication of infection and many deaths could be prevented with earlier identification and more targeted therapies.

Link: https://www.nature.com/articles/s41591-018-0213-5

#medical #health

Christie’s has sold its first piece of AI art, a canvas named the Portrait of Edmond Belamy, for $432,500

Investigation by Verge: https://www.theverge.com/2018/10/23/18013190/ai-art-portrait-auction-christies-belamy-obvious-robbie-barrat-gans

GitHub: https://github.com/robbiebarrat/art-DCGAN

Dynamic Meta-Embeddings for Improved Sentence Representations

While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic meta-embeddings, a simple yet effective method for the supervised learning of embedding ensembles, which leads to state-of-the-art performance within the same model class on a variety of tasks. We subsequently show how the technique can be used to shed new light on the usage of word embeddings in NLP systems.

Paper: https://research.fb.com/wp-content/uploads/2018/10/Dynamic-Meta-Embeddings-for-Improved-Sentence-Representations.pdf
Link: https://research.fb.com/publications/dynamic-meta-embeddings-for-improved-sentence-representations/

P.S. Note the date of the publication

#embeddings #NLP #facebook

Facebook is open-sourcing QNNPACK, a kernel library that is optimized for mobile AI.

Site: https://code.fb.com/ml-applications/qnnpack/
Github: https://github.com/pytorch/QNNPACK

#dl #mobile #facebook

Really scary

An agent which learned to play Mario without rewards. Instead, it was incentivized to avoid "boredom" (that is, getting into states where it can predict what will happen next). Discovered warp levels, how to defeat bosses, etc.

Link: https://blog.openai.com/reinforcement-learning-with-prediction-based-rewards/

#RL #openai

Facebook open sourced Horizon, an end-to-end applied reinforcement learning platform built on #PyTorch 1.0. Horizon uses RL to optimize systems in large-scale production environments and we're excited to make it accessible to anyone using #RL at scale.

https://code.fb.com/ml-applications/horizon/

#facebook

XNLI dataset published by Facebook AI & NYU.

New dataset have been released recently to promote cross-lingual approaches to natural language understanding (#NLU).

This dataset builds on the commonly used Multi-Genre Natural Language Inference (MultiNLI) corpus, adding 14 languages to that English-only data set, including two low-resource languages: Swahili and Urdu.

Link: https://code.fb.com/ai-research/xlni/

#NLP #facebook

#DeepMind ’s library for deep learning on graphs.


ArXiV: https://arxiv.org/abs/1806.01261
Github: https://github.com/deepmind/graph_nets

Reversible RNNs

Paper about how to reduce memory costs of GRU and LSTM networks by 10-15x without loss in performance. Also 5-10x for attention-based architectures. New paper with Matt MacKay, Paul Vicol, and Jimmy Ba, to appear at NIPS.

Link: https://arxiv.org/abs/1810.10999

#dl #RNN #NIPS2018

Faster R-CNN and Mask R-CNN in #PyTorch 1.0

Another release from #Facebook.

Mask R-CNN Benchmark: a fast and modular implementation for Faster R-CNN and Mask R-CNN written entirely in @PyTorch 1.0. It brings up to 30% speedup compared to mmdetection during training.

Webcam demo and ipynb file are available.

Github: https://github.com/facebookresearch/maskrcnn-benchmark

#CNN #CV #segmentation #detection

Mask R-CNN Benchmark Demo

A set of best where-to-start-with-python resources.

This is the collection of beginners resources from a tweet by fast.ai cofounder, covering any resource which helped people to learn python from scratch.

https://telegra.ph/A-collection-of-where-to-start-python-resources-11-05

#beginner #novice #CS #python #tutorial