Clarifying exceptions and visualizing tensor operations in deep learning code.
https://explained.ai/tensor-sensor/index.html
https://explained.ai/tensor-sensor/index.html
Understanding self-supervised and contrastive learning with "Bootstrap Your Own Latent" (BYOL)
https://untitled-ai.github.io/understanding-self-supervised-contrastive-learning.html
https://untitled-ai.github.io/understanding-self-supervised-contrastive-learning.html
Reinforcement learning is supervised learning on optimized data
https://bair.berkeley.edu/blog/2020/10/13/supervised-rl/
https://bair.berkeley.edu/blog/2020/10/13/supervised-rl/
Measuring Gendered Correlations in Pre-trained NLP Models
https://ai.googleblog.com/2020/10/measuring-gendered-correlations-in-pre.html
https://ai.googleblog.com/2020/10/measuring-gendered-correlations-in-pre.html
research.google
Measuring Gendered Correlations in Pre-trained NLP Models
Posted by Kellie Webster, Software Engineer, Google Research Natural language processing (NLP) has seen significant progress over the past several ...
Recreating Historical Streetscapes Using Deep Learning and Crowdsourcing
https://ai.googleblog.com/2020/10/recreating-historical-streetscapes.html
https://ai.googleblog.com/2020/10/recreating-historical-streetscapes.html
research.google
Recreating Historical Streetscapes Using Deep Learning and Crowdsourcing
Posted by Raimondas Kiveris, Software Engineer, Google Research For many, gazing at an old photo of a city can evoke feelings of both nostalgia and...
AdaBelief Optimizer: fast as Adam, generalizes as good as SGD, and sufficiently stable to train GANs.
https://juntang-zhuang.github.io/adabelief/
Github: https://github.com/juntang-zhuang/Adabelief-Optimizer#a-quick-look-at-the-algorithm
Paper: https://arxiv.org/abs/2010.07468v1
https://juntang-zhuang.github.io/adabelief/
Github: https://github.com/juntang-zhuang/Adabelief-Optimizer#a-quick-look-at-the-algorithm
Paper: https://arxiv.org/abs/2010.07468v1
juntang-zhuang.github.io
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients
Crack the top 40 machine learning interview questions
https://levelup.gitconnected.com/crack-the-top-40-machine-learning-interview-questions-a7526335bcdc
https://levelup.gitconnected.com/crack-the-top-40-machine-learning-interview-questions-a7526335bcdc
Medium
Crack the top 40 machine learning interview questions
Today, take a deep dive into the top 40 machine learning interview questions for any FAANG company.
Contrastive Learning with Hard Negative Samples
Github: https://github.com/joshr17/HCL
Paper: https://arxiv.org/pdf/2010.04592.pdf
Github: https://github.com/joshr17/HCL
Paper: https://arxiv.org/pdf/2010.04592.pdf
Containerized end-to-end analytics of Spotify data using Python
https://pythonawesome.com/containerized-end-to-end-analytics-of-spotify-data-using-python/
https://pythonawesome.com/containerized-end-to-end-analytics-of-spotify-data-using-python/
Announcing the NVIDIA NVTabular Open Beta with Multi-GPU Support and New Data Loaders
https://developer.nvidia.com/blog/announcing-the-nvtabular-open-beta-with-multi-gpu-support-and-new-data-loaders/
https://developer.nvidia.com/blog/announcing-the-nvtabular-open-beta-with-multi-gpu-support-and-new-data-loaders/
Forwarded from TensorFlow
Rethinking Attention with Performers
https://ai.googleblog.com/2020/10/rethinking-attention-with-performers.html
@tensorflowblog
https://ai.googleblog.com/2020/10/rethinking-attention-with-performers.html
@tensorflowblog
research.google
Rethinking Attention with Performers
Posted by Krzysztof Choromanski and Lucy Colwell, Research Scientists, Google Research Transformer models have achieved state-of-the-art results ac...
FaceShifter — Unofficial PyTorch Implementation
Github: https://github.com/mindslab-ai/faceshifter
Paper: https://arxiv.org/abs/1912.13457
Github: https://github.com/mindslab-ai/faceshifter
Paper: https://arxiv.org/abs/1912.13457
Multilingual T5 (mT5) is a massively multilingual pretrained text-to-text transformer model
Github: https://github.com/google-research/multilingual-t5
Paper: https://arxiv.org/abs/2010.11934v1
Github: https://github.com/google-research/multilingual-t5
Paper: https://arxiv.org/abs/2010.11934v1
GitHub
GitHub - google-research/multilingual-t5
Contribute to google-research/multilingual-t5 development by creating an account on GitHub.
Contrastive learning of general purpose audio representations
https://github.com/google-research/google-research/tree/master/cola
https://github.com/google-research/google-research/tree/master/cola
Bitcoin Trading is Irrational! An Analysis of the Disposition Effect in Bitcoin.
Github: https://github.com/jschatzmann/CryptoDisposition
Paper: https://arxiv.org/abs/2010.12415v1
Github: https://github.com/jschatzmann/CryptoDisposition
Paper: https://arxiv.org/abs/2010.12415v1
Trajectory-wise Multiple Choice Learning for Generalization in Reinforcement Learning
https://github.com/younggyoseo/trajectory_mcl
https://github.com/younggyoseo/trajectory_mcl
Easy-to-interpret neurons may hinder learning in deep neural networks
https://ai.facebook.com/blog/easy-to-interpret-neurons-may-hinder-learning-in-deep-neural-networks/
https://ai.facebook.com/blog/easy-to-interpret-neurons-may-hinder-learning-in-deep-neural-networks/
Facebook
Easy-to-interpret neurons may hinder learning in deep neural networks
What does an AI model “understand” and why? A long-held belief is there are easy-to-interpret neurons -- or “class selective” neurons. For instance, finding neurons that
Abdominal Organ Segmentation A Solved Problem?
Github: https://github.com/MIC-DKFZ/nnunet
Paper: https://arxiv.org/abs/2010.14808v1
@ArtificialIntelligencedl
Github: https://github.com/MIC-DKFZ/nnunet
Paper: https://arxiv.org/abs/2010.14808v1
@ArtificialIntelligencedl
GitHub
GitHub - MIC-DKFZ/nnUNet
Contribute to MIC-DKFZ/nnUNet development by creating an account on GitHub.