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
GitHub: https://github.com/yunjey/StarGAN
Arxiv: https://arxiv.org/abs/1711.09020
#deeplearning #gan #cv
GitHub
GitHub - yunjey/stargan: StarGAN - Official PyTorch Implementation (CVPR 2018)
StarGAN - Official PyTorch Implementation (CVPR 2018) - GitHub - yunjey/stargan: StarGAN - Official PyTorch Implementation (CVPR 2018)
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
https://medium.com/@francois.chollet/the-impossibility-of-intelligence-explosion-5be4a9eda6ec
Medium
The implausibility of intelligence explosion
In 1965, I. J. Good described for the first time the notion of “intelligence explosion”, as it relates to artificial intelligence (AI):
#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
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
stanfordmlgroup.github.io
Improving Palliative Care with Deep Learning
Improving Palliative Care with Deep Learning.
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
https://www.youtube.com/watch?v=XOxxPcy5Gr4
#GAN #youtube
YouTube
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Submission video of our paper, published at ICLR 2018. Please see the final version at https://youtu.be/G06dEcZ-QTg
Authors:
Tero Karras (NVIDIA)
Timo Aila (NVIDIA)
Samuli Laine (NVIDIA)
Jaakko Lehtinen (NVIDIA and Aalto University)
For business inquiries…
Authors:
Tero Karras (NVIDIA)
Timo Aila (NVIDIA)
Samuli Laine (NVIDIA)
Jaakko Lehtinen (NVIDIA and Aalto University)
For business inquiries…
AI index report, demonstrating hype around AI techonologies: https://aiindex.org/2017-report.pdf
This media is not supported in your browser
VIEW IN TELEGRAM
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
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
GitHub
GitHub - NVIDIA/pix2pixHD: Synthesizing and manipulating 2048x1024 images with conditional GANs
Synthesizing and manipulating 2048x1024 images with conditional GANs - NVIDIA/pix2pixHD
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
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
einstein.ai
Salesforce research
When humans generate novel neural architectures, they go through a surprisingly large amount of trial and error. In an optimal world, the neural networks would explore potential architectures themselves.
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
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
Facebook
Data Challenges
The flagrant case of discrimination against participants from Russia CrowdANALYTIX Solver Community launched the competition From AO to AI: Predicting How Points End in Tennis with total prize pool...
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
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
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
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
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
CoreNLP
High-performance human language analysis tools, now with native deep learning modules in Python, available in many human languages.
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
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
PyImageSearch
Deep learning in production with Keras, Redis, Flask, and Apache - PyImageSearch
This guide will show you how to deploy and scale your deep learning model in production using Keras, Redis, Flask, and Apache.
This media is not supported in your browser
VIEW IN TELEGRAM
😂😭 like back to school
Forwarded from Karim Iskakov - канал (Karim Iskakov)
This media is not supported in your browser
VIEW IN TELEGRAM
"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
🔎 http://arxiv.org/abs/1710.10196
📉 @loss_function_porn