StarGAN — a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model.

GitHub: https://github.com/yunjey/StarGAN
Arxiv: https://arxiv.org/abs/1711.09020

#deeplearning #gan #cv

An article about the impossibility of intelligence explosion. There will be no singularity or significant breakthrough and humanity will die off becuase of sun explosion.

https://medium.com/@francois.chollet/the-impossibility-of-intelligence-explosion-5be4a9eda6ec

#DeepLearning predicts when patients die with Average Precision 0.69 (that’s high).

Andrew Ng announced new project in his twitter: ML to help prioritize palliative (end-of-life) care. Model uses an 18-layer Deep Neural Network that inputs the EHR data of a patient, and outputs the probability of death in the next 3-12 months.

The trained model achieves an AUROC score of 0.93 and an Average Precision score of 0.69 on cross validation.

Site: https://stanfordmlgroup.github.io/projects/improving-palliative-care/
Arxiv: https://arxiv.org/abs/1711.06402

#project #DSinthewild #casestudy

Video displaying progress of GANs for photo generation. Now you can use neural networks to generate HD photo of a person who never existed.

https://www.youtube.com/watch?v=XOxxPcy5Gr4

#GAN #youtube

AI index

AI index report, demonstrating hype around AI techonologies: https://aiindex.org/2017-report.pdf

pix2pix Demo: Neural network generates cityscape based on the input label map.

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs.

Now mankind can generate content for social networks without taking photoes.

Github: https://github.com/NVIDIA/pix2pixHD
Arxiv: https://arxiv.org/pdf/1711.11585.pdf

Another paper on automl: Neural Nets learning to design Neural Nets.

A reinforcement learning agent that learns to program new neural network architectures.
Same/better results as LSTMs but with funky nonlinearities (sine, SeLus, etc) and new connections that result in different activation patterns.

Arxiv: https://arxiv.org/abs/1712.07316
Post: https://einstein.ai/research/domain-specific-language-for-automated-rnn-architecture-search

Unfortunately, discrimination against ML competition participants becomes more frequent. CrowdANALYTIX recently launched a competition that simply bans different countries from opportunity to participate, this time including Russia.

Spread the word so that we could make Data Science and ML more open, without obsolete discriminatory rules on competition platforms:
https://www.facebook.com/DataChallenges/photos/a.136318350296824.1073741827.136313013630691/182693245659334/?type=3&theater

Graph shows what people really mean when they use vague terminology describing the probability of an event.

Baidu’s neural network based system learned to "clone" a voice with less than a minute of audio data from the speaker.

Explaining website: http://research.baidu.com/neural-voice-cloning-samples/
Paper: https://arxiv.org/pdf/1802.06006.pdf

#DeepLearning #Voice #Speech

«Efficient Neural Architecture Search via Parameters Sharing»

Authors reduced the computational requirement (GPU-hrs) of standard Neural Architecture Search by 1000x via parameter sharing between models that are subgraphs within a large computational graph. ENAS achieves SOTA on PTB language modeling among all methods without post-training processing and strong performance on CIFAR-10.

Link: https://arxiv.org/pdf/1802.03268.pdf

#arxiv #optimization #neuralnetworks

«A Closed-form Solution to Photorealistic Image Stylization» — new release by NVidia, exploring photorealistic style transfer.

The proposed algorithm consists of a stylization step and a smoothing step. While the stylization step transfers the style of the reference photo to the content photo, the smoothing step encourages spatially consistent stylizations.

Arxiv: https://arxiv.org/abs/1802.06474

Pictures: https://raw.githubusercontent.com/NVIDIA/FastPhotoStyle/master/alg_in_action.png

Most common libraries for Natural Language Processing:

CoreNLP from Stanford group:
http://stanfordnlp.github.io/CoreNLP/index.html

NLTK, the most widely-mentioned NLP library for Python:
http://www.nltk.org/

TextBlob, a user-friendly and intuitive NLTK interface:
https://textblob.readthedocs.io/en/dev/index.html

Gensim, a library for document similarity analysis:
https://radimrehurek.com/gensim/

SpaCy, an industrial-strength NLP library built for performance:
https://spacy.io/docs/

Source: https://itsvit.com/blog/5-heroic-tools-natural-language-processing/

#nlp #digest #libs

How to find out that there is something wrong with your child:

It is important not only to build and train a model, but also to serve it in the production. Thus, this article might be a great starting point:

Deep learning in production with Keras, Redis, Flask, and Apache

https://www.pyimagesearch.com/2018/02/05/deep-learning-production-keras-redis-flask-apache/?utm_source=opendatascience

#dl #deeplearning #keras #production

😂😭 like back to school

"GAN with Improved quality, stability, and variation by NVidia. None of the people in this video ever really existed. Spectacular and creepy"
🔎 http://arxiv.org/abs/1710.10196
📉 @loss_function_porn