ββTransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
Paper: https://arxiv.org/pdf/1904.09571v1.pdf
#GAN #cv #dl
Paper: https://arxiv.org/pdf/1904.09571v1.pdf
#GAN #cv #dl
A Recipe for Training Neural Networks by Andrej Karpathy
New article written by Andrej Karpathy distilling a bunch of useful heuristics for training neural nets. The post is full of real-world knowledge and how-to details that are not taught in books and often take endless hours to learn the hard way.
Link: https://karpathy.github.io/2019/04/25/recipe/
#tipsandtricks #karpathy #tutorial #nn #ml #dl
New article written by Andrej Karpathy distilling a bunch of useful heuristics for training neural nets. The post is full of real-world knowledge and how-to details that are not taught in books and often take endless hours to learn the hard way.
Link: https://karpathy.github.io/2019/04/25/recipe/
#tipsandtricks #karpathy #tutorial #nn #ml #dl
karpathy.github.io
A Recipe for Training Neural Networks
Musings of a Computer Scientist.
OpenAIβs MuseNet architecture to generate music.
#MuseNet β neural network which discovered how to generate music from first 5 or so notes, using many different instruments and styles.
Post: https://openai.com/blog/musenet/
MuseNet will play an experimental concert today from 12β3pm PT on livestream: http://twitch.tv/openai
#audiolearning #musicgeneration #OpenAI #soundgeneration
#MuseNet β neural network which discovered how to generate music from first 5 or so notes, using many different instruments and styles.
Post: https://openai.com/blog/musenet/
MuseNet will play an experimental concert today from 12β3pm PT on livestream: http://twitch.tv/openai
#audiolearning #musicgeneration #OpenAI #soundgeneration
Openai
MuseNet
Weβve created MuseNet, a deep neural network that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles. MuseNet was not explicitly programmed with our understanding of musicβ¦
All videos & slides from Scaled Machine Learning Conference 2019
YouTube playlist: https://www.youtube.com/playlist?list=PLRM2gQVaW_wWXoUnSfZTxpgDmNaAS1RtG
#Facebook #dl #ScaledML2019
YouTube playlist: https://www.youtube.com/playlist?list=PLRM2gQVaW_wWXoUnSfZTxpgDmNaAS1RtG
#Facebook #dl #ScaledML2019
YouTube
ScaledML 2019 - YouTube
New interactive annotation approach
Claimed to outperform Polygon-RNN++ and being 10x faster.
ArXiV: https://arxiv.org/pdf/1903.06874.pdf
YouTube: https://www.youtube.com/watch?v=ycD2BtO-QzU
Code: https://github.com/fidler-lab/curve-gcn
#PyTorch #annotation #release
Claimed to outperform Polygon-RNN++ and being 10x faster.
ArXiV: https://arxiv.org/pdf/1903.06874.pdf
YouTube: https://www.youtube.com/watch?v=ycD2BtO-QzU
Code: https://github.com/fidler-lab/curve-gcn
#PyTorch #annotation #release
YouTube
Fast Interactive Object Annotation with Curve-GCN
Paper is accepted by Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Paper link: https://arxiv.org/abs/1903.06874
Code is available at: https://github.com/fidler-lab/curve-gcn
Paper link: https://arxiv.org/abs/1903.06874
Code is available at: https://github.com/fidler-lab/curve-gcn
ββODE DL paper with overview
This paper recieved award at #NeurIPS2018. Main idea: defining a deep residual network as a continuously evolving system & instead of updating the hidden units layer by layer, define their derivative with respect to depth instead.
ArXiV: https://arxiv.org/pdf/1806.07366.pdf
GitHub: https://github.com/rtqichen/torchdiffeq
Overview: https://rkevingibson.github.io/blog/neural-networks-as-ordinary-differential-equations/
#ODE #DL #NeurIPS
This paper recieved award at #NeurIPS2018. Main idea: defining a deep residual network as a continuously evolving system & instead of updating the hidden units layer by layer, define their derivative with respect to depth instead.
ArXiV: https://arxiv.org/pdf/1806.07366.pdf
GitHub: https://github.com/rtqichen/torchdiffeq
Overview: https://rkevingibson.github.io/blog/neural-networks-as-ordinary-differential-equations/
#ODE #DL #NeurIPS
Great visualization of DBSCAN
DBSCAN β is fast and rather reliable #clustering algorithm. It can outperform classical K-means in some cases and icredibly useful in some cases. This interactive demo helps to understand how algorithm really works.
Link: https://www.naftaliharris.com/blog/visualizing-dbscan-clustering/
#ML #dbscan
DBSCAN β is fast and rather reliable #clustering algorithm. It can outperform classical K-means in some cases and icredibly useful in some cases. This interactive demo helps to understand how algorithm really works.
Link: https://www.naftaliharris.com/blog/visualizing-dbscan-clustering/
#ML #dbscan
GAN for retail marketing images generation
Startup that uses GANs to generate retail marketing images, has raised $17M. What a smart use for GANs.
https://venturebeat.com/2019/04/24/vue-ai-raises-17-million-for-ai-driven-retail-products/
#GAN #startup #fundraising
Startup that uses GANs to generate retail marketing images, has raised $17M. What a smart use for GANs.
https://venturebeat.com/2019/04/24/vue-ai-raises-17-million-for-ai-driven-retail-products/
#GAN #startup #fundraising
VentureBeat
Vue.ai raises $17 million for AI-driven retail products
Vue.ai, a subbrand of India-U.S. startup Mad Street Den, has raised $17 million in venture capital, which it says will be used to grow its team.
Machine Learning Workflows
Pretty articel about how machine learning / AI works in the organization.
Link: https://skymind.ai/wiki/machine-learning-workflow
#management #production #workflow
Pretty articel about how machine learning / AI works in the organization.
Link: https://skymind.ai/wiki/machine-learning-workflow
#management #production #workflow
Skymind
Machine Learning Workflows
Workflows for moving Machine Learning to a business production environment.
Modeling User Exposure in Recommendation
On using latent variables for exposure of an user to an item to build a better recommendation systems.
Link: https://arxiv.org/abs/1510.07025
#recommender #RS
On using latent variables for exposure of an user to an item to build a better recommendation systems.
Link: https://arxiv.org/abs/1510.07025
#recommender #RS
arXiv.org
Modeling User Exposure in Recommendation
Collaborative filtering analyzes user preferences for items (e.g., books,
movies, restaurants, academic papers) by exploiting the similarity patterns
across users. In implicit feedback settings,...
movies, restaurants, academic papers) by exploiting the similarity patterns
across users. In implicit feedback settings,...
How to hide from the AI surveillance state with a color printout
MITβs team studied how to fool camera with and #adversarial print, exploiting the fact that #CNN can be tricked by adversarial examples into recognizing something wrong or not recongnizing image at all.
Link: https://www.technologyreview.com/f/613409/how-to-hide-from-the-ai-surveillance-state-with-a-color-printout/
#CV #DL #MIT
MITβs team studied how to fool camera with and #adversarial print, exploiting the fact that #CNN can be tricked by adversarial examples into recognizing something wrong or not recongnizing image at all.
Link: https://www.technologyreview.com/f/613409/how-to-hide-from-the-ai-surveillance-state-with-a-color-printout/
#CV #DL #MIT
MIT Technology Review
How to hide from the AI surveillance state with a color printout
AI-powered video technology is becoming ubiquitous, tracking our faces and bodies through stores, offices, and public spaces. In some countries the technology constitutes a powerful new layer of policing and government surveillance. Fortunately, as some researchersβ¦
πΉVideo about best chalk for the blackboard.
This is the story of chalk. Not just any chalk, but a Japanese brand called Hagoromo, which mathematician Satyan Devadoss dubbed "the Michael Jordan of chalk, the Rolls Royce of chalk" Then the company decided to stop making chalk. So mathematicians began hoarding it.
YouTube: https://www.youtube.com/watch?v=PhNUjg9X4g8
This is the story of chalk. Not just any chalk, but a Japanese brand called Hagoromo, which mathematician Satyan Devadoss dubbed "the Michael Jordan of chalk, the Rolls Royce of chalk" Then the company decided to stop making chalk. So mathematicians began hoarding it.
YouTube: https://www.youtube.com/watch?v=PhNUjg9X4g8
YouTube
Why the Worldβs Best Mathematicians Are Hoarding Chalk
Once upon a time, not long ago, the math world fell in love ... with a chalk. But not just any chalk! This was Hagoromo: a Japanese brand so smooth, so perfect that some wondered if it was made from the tears of angels. Pencils down, please, as we tell theβ¦
Distributed Representations of Words and Phrases and their Compositionality
Several extensions to #SkipGram that improve both the quality of the vectors and the training speed
ArXiV: https://arxiv.org/abs/1310.4546
#NLP #oldenough
Several extensions to #SkipGram that improve both the quality of the vectors and the training speed
ArXiV: https://arxiv.org/abs/1310.4546
#NLP #oldenough
arXiv.org
Distributed Representations of Words and Phrases and their Compositionality
The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic...
ββReal-Time Patch-Based Stylization of Portraits Using Generative Adversarial Network
Face photo stylization from #Snap research team. Rather fast solution with demo available.
Demo: http://facestyle.org/#
Paper: https://dcgi.fel.cvut.cz/home/sykorad/Futschik19-NPAR.pdf
YouTube: https://www.youtube.com/watch?v=G3nwTSd3_XA
#GAN #DL #Styletransfer
Face photo stylization from #Snap research team. Rather fast solution with demo available.
Demo: http://facestyle.org/#
Paper: https://dcgi.fel.cvut.cz/home/sykorad/Futschik19-NPAR.pdf
YouTube: https://www.youtube.com/watch?v=G3nwTSd3_XA
#GAN #DL #Styletransfer
Speech synthesis from neural decoding of spoken sentences
Researchers tapped the brains of five epilepsy patients who had been implanted with electrodes to map the source of seizures, according to a paper published by #Nature. During a lull in the procedure, they had the patients read English-language texts aloud. They recorded the fluctuating voltage as the brain controlled the muscles involved in speaking. Later, they fed the voltage measurements into a synthesizer.
Nature: https://www.nature.com/articles/s41586-019-1119-1
Paper: https://www.biorxiv.org/content/biorxiv/early/2018/11/29/481267.full.pdf
YouTube: https://www.youtube.com/watch?v=kbX9FLJ6WKw
#DeepDiveWeekly #DL #speech #audiolearning
Researchers tapped the brains of five epilepsy patients who had been implanted with electrodes to map the source of seizures, according to a paper published by #Nature. During a lull in the procedure, they had the patients read English-language texts aloud. They recorded the fluctuating voltage as the brain controlled the muscles involved in speaking. Later, they fed the voltage measurements into a synthesizer.
Nature: https://www.nature.com/articles/s41586-019-1119-1
Paper: https://www.biorxiv.org/content/biorxiv/early/2018/11/29/481267.full.pdf
YouTube: https://www.youtube.com/watch?v=kbX9FLJ6WKw
#DeepDiveWeekly #DL #speech #audiolearning
Nature
Speech synthesis from neural decoding of spoken sentences
Nature - A neural decoder uses kinematic and sound representations encoded in human cortical activity to synthesize audible sentences, which are readily identified and transcribed by listeners.
Unsupervised community detection with modularity-based attention model
Searching for communities on graphs is hard -> no clear loss, discrete labels (usually). What we do: use soft log-liklehood approximation with tricks + GNNs to try to match classical SOTA.
Paper: https://rlgm.github.io/papers/37.pdf
#ICLR2019 #GNN #GraphLearning
Searching for communities on graphs is hard -> no clear loss, discrete labels (usually). What we do: use soft log-liklehood approximation with tricks + GNNs to try to match classical SOTA.
Paper: https://rlgm.github.io/papers/37.pdf
#ICLR2019 #GNN #GraphLearning
π1
The lottery ticket hypothesis: finding sparse, trainable neural networks
Best paper award at #ICLR2019 main idea: dense, randomly-initialized, networks contain sparse subnetworks that trained in isolation reach test accuracy comparable to the original network. Thus compressing the original network up to 10% its original size.
Paper: https://arxiv.org/pdf/1803.03635.pdf
#nn #research
Best paper award at #ICLR2019 main idea: dense, randomly-initialized, networks contain sparse subnetworks that trained in isolation reach test accuracy comparable to the original network. Thus compressing the original network up to 10% its original size.
Paper: https://arxiv.org/pdf/1803.03635.pdf
#nn #research
ββModeling Price with Regularized Linear Model & #XGBoost
Great example of applicable research for #production #ML.
Link: https://www.kdnuggets.com/2019/05/modeling-price-regularized-linear-model-xgboost.html
#novice #entrylevel
Great example of applicable research for #production #ML.
Link: https://www.kdnuggets.com/2019/05/modeling-price-regularized-linear-model-xgboost.html
#novice #entrylevel
Forwarded from Hacker News
The Feynman Lectures on Physics now free (Score: 100+ in 17 hours)
Link: https://readhacker.news/s/43fFn
Comments: https://readhacker.news/c/43fFn
Link: https://readhacker.news/s/43fFn
Comments: https://readhacker.news/c/43fFn
ββπ£ Conversational AI building tutorial, open-source code & demo!
Building a SOTA Conversational AI with transfer learning & OpenAI GPT models
Code/pretrained model from NeurIPS 2018 ConvAI2 competition model, SOTA on automatic track
Detailed Tutorial w. code
Tutorial: https://medium.com/huggingface/how-to-build-a-state-of-the-art-conversational-ai-with-transfer-learning-2d818ac26313
Demo: http://convai.huggingface.co
Code: https://github.com/huggingface/transfer-learning-conv-ai
#tutorial #novice
Building a SOTA Conversational AI with transfer learning & OpenAI GPT models
Code/pretrained model from NeurIPS 2018 ConvAI2 competition model, SOTA on automatic track
Detailed Tutorial w. code
Tutorial: https://medium.com/huggingface/how-to-build-a-state-of-the-art-conversational-ai-with-transfer-learning-2d818ac26313
Demo: http://convai.huggingface.co
Code: https://github.com/huggingface/transfer-learning-conv-ai
#tutorial #novice
Forwarded from Karim Iskakov - ΠΊΠ°Π½Π°Π» (karfly_bot)
This media is not supported in your browser
VIEW IN TELEGRAM
"I'm very proud to share our first paper Learnable Triangulation of Human Pose. We smashed previous state of the art (by ~2.5x) in multi-view 3D human pose estimation. Like, share, cite!"
π saic-violet.github.io/learnable-triangulation
π arxiv.org/abs/1905.05754
π @loss_function_porn
π saic-violet.github.io/learnable-triangulation
π arxiv.org/abs/1905.05754
π @loss_function_porn