AutoFlip: An Open Source Framework for Intelligent Video Reframing
https://ai.googleblog.com/2020/02/autoflip-open-source-framework-for.html
https://ai.googleblog.com/2020/02/autoflip-open-source-framework-for.html
research.google
AutoFlip: An Open Source Framework for Intelligent Video Reframing
Posted by Nathan Frey, Senior Software Engineer, Google Research, Los Angeles and Zheng Sun, Senior Software Engineer, Google Research, Mountain Vi...
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning
https://senya-ashukha.github.io/pitfalls-uncertainty&ensembling
https://senya-ashukha.github.io/pitfalls-uncertainty&ensembling
Ashukha
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning
Optimizing infrastructure for neural recommendation at scale
https://ai.facebook.com/blog/-optimizing-infrastructure-for-neural-recommendation-at-scale/
https://ai.facebook.com/blog/-optimizing-infrastructure-for-neural-recommendation-at-scale/
Official Tensorflow implementation of the paper "Y-Autoencoders: disentangling latent representations via sequential-encoding»
Github: https://github.com/mpatacchiola/Y-AE
Paper: https://arxiv.org/abs/1907.10949
Github: https://github.com/mpatacchiola/Y-AE
Paper: https://arxiv.org/abs/1907.10949
ZeRO & DeepSpeed: New system optimizations enable training models with over 100 billion parameters
https://www.microsoft.com/en-us/research/blog/zero-deepspeed-new-system-optimizations-enable-training-models-with-over-100-billion-parameters/
https://www.microsoft.com/en-us/research/blog/zero-deepspeed-new-system-optimizations-enable-training-models-with-over-100-billion-parameters/
Microsoft Research
ZeRO & DeepSpeed: New system optimizations enable training models with over 100 billion parameters - Microsoft Research
The latest trend in AI is that larger natural language models provide better accuracy; however, larger models are difficult to train because of cost, time, and ease of code integration. Microsoft is releasing an open-source library called DeepSpeed, which…
How to implement a YOLO (v3) object detector from scratch in PyTorch: Part 1
https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/
https://blog.paperspace.com/how-to-implement-a-yolo-object-detector-in-pytorch/
Paperspace by DigitalOcean Blog
Tutorial on implementing YOLO v3 from scratch in PyTorch
Tutorial on building YOLO v3 detector from scratch detailing how to create the network architecture from a configuration file, load the weights and designing input/output pipelines.
How to Develop a Probabilistic Model of Breast Cancer Patient Survival
https://machinelearningmastery.com/how-to-develop-a-probabilistic-model-of-breast-cancer-patient-survival/
https://machinelearningmastery.com/how-to-develop-a-probabilistic-model-of-breast-cancer-patient-survival/
MachineLearningMastery.com
How to Develop a Probabilistic Model of Breast Cancer Patient Survival - MachineLearningMastery.com
Developing a probabilistic model is challenging in general, although it is made more so when there is skew in the distribution of cases, referred to as an imbalanced dataset.
The Haberman Dataset describes the five year or greater survival of breast cancer…
The Haberman Dataset describes the five year or greater survival of breast cancer…
Generating Diverse Synthetic Medical Image Data for Training Machine Learning Models
https://ai.googleblog.com/2020/02/generating-diverse-synthetic-medical.html
https://ai.googleblog.com/2020/02/generating-diverse-synthetic-medical.html
research.google
Generating Diverse Synthetic Medical Image Data for Training Machine Learning Mo
Posted by Timo Kohlberger and Yuan Liu, Software Engineers, Google Health The progress in machine learning (ML) for medical imaging that helps do...
A high level framework and library for running, training, and deploying state-of-the- art Natural Language Processing (NLP) models for end to end tasks.
https://github.com/Novetta/adaptnlp
https://github.com/Novetta/adaptnlp
GitHub
GitHub - Novetta/adaptnlp: An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning…
An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models. - GitHub - Novetta/adaptnlp: An easy to use Natur...
IBM Data Science and AI Programs Free for 30 Days
https://onlinecoursesgalore.com/ibm-data-science-ai-coursera/
Coursera: https://www.coursera.org/promo/ibmdscommunity?ranMID=40328&ranEAID
https://onlinecoursesgalore.com/ibm-data-science-ai-coursera/
Coursera: https://www.coursera.org/promo/ibmdscommunity?ranMID=40328&ranEAID
Online Courses Galore
IBM Data Science and AI Programs on Coursera Free for 30 Days
Coursera 30 days of free access to IBM data science and artificial intelligence specialization & professional cert programs until June 2022
Deep Learning-Based Feature Extraction in Iris Recognition: Use Existing Models, Fine-tune or Train From Scratch?
Code: https://github.com/BoydAidan/BTAS2019DeepFeatureExtraction
Article: https://arxiv.org/abs/2002.08916v1
Code: https://github.com/BoydAidan/BTAS2019DeepFeatureExtraction
Article: https://arxiv.org/abs/2002.08916v1
Enhancing the Research Community’s Access to Street View Panoramas for Language Grounding Tasks
https://ai.googleblog.com/2020/02/enhancing-research-communitys-access-to.html
https://ai.googleblog.com/2020/02/enhancing-research-communitys-access-to.html
Google AI Blog
Enhancing the Research Community’s Access to Street View Panoramas for Language Grounding Tasks
Posted by Harsh Mehta, Software Engineer and Jason Baldridge, Research Scientist, Google Research Significant advances continue to be ma...
FastMRI leverages adversarial learning to remove image artifacts
https://ai.facebook.com/blog/fastmri-leverages-adversarial-learning-to-remove-image-artifacts/
Paper: https://arxiv.org/abs/2001.08699
https://ai.facebook.com/blog/fastmri-leverages-adversarial-learning-to-remove-image-artifacts/
Paper: https://arxiv.org/abs/2001.08699
Develop a Model for the Imbalanced Classification of Good and Bad Credit
https://machinelearningmastery.com/imbalanced-classification-of-good-and-bad-credit/
https://machinelearningmastery.com/imbalanced-classification-of-good-and-bad-credit/
MachineLearningMastery.com
Develop a Model for the Imbalanced Classification of Good and Bad Credit - MachineLearningMastery.com
Misclassification errors on the minority class are more important than other types of prediction errors for some imbalanced classification tasks. One example is the problem of classifying bank customers as to whether they should receive a loan or not. Giving…
Powered by AI: Turning any 2D photo into 3D using convolutional neural nets
https://ai.facebook.com/blog/-powered-by-ai-turning-any-2d-photo-into-3d-using-convolutional-neural-nets/
https://ai.facebook.com/blog/-powered-by-ai-turning-any-2d-photo-into-3d-using-convolutional-neural-nets/
Facebook
Powered by AI: Turning any 2D photo into 3D using convolutional neural nets
We have created a new AI-powered tool that can turn virtually any standard 2D picture into a 3D image.
Ultra-High Resolution Image Analysis with Mesh-TensorFlow
https://ai.googleblog.com/2020/02/ultra-high-resolution-image-analysis.html
https://ai.googleblog.com/2020/02/ultra-high-resolution-image-analysis.html
Googleblog
Ultra-High Resolution Image Analysis with Mesh-TensorFlow
Transformers are Graph Neural Networks
https://graphdeeplearning.github.io/post/transformers-are-gnns/
https://graphdeeplearning.github.io/post/transformers-are-gnns/
NTU Graph Deep Learning Lab
Transformers are Graph Neural Networks | NTU Graph Deep Learning Lab
Engineer friends often ask me: Graph Deep Learning sounds great, but are there any big commercial success stories? Is it being deployed in practical applications?
Besides the obvious ones–recommendation systems at Pinterest, Alibaba and Twitter–a slightly…
Besides the obvious ones–recommendation systems at Pinterest, Alibaba and Twitter–a slightly…
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
Code: https://github.com/microsoft/unilm
Paper: https://arxiv.org/abs/2002.12804v1
Code: https://github.com/microsoft/unilm
Paper: https://arxiv.org/abs/2002.12804v1
GitHub
GitHub - microsoft/unilm: Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities - microsoft/unilm
Differentiable Convex Optimization Layers
CVXPY creates powerful new PyTorch and TensorFlow layers
https://locuslab.github.io/2019-10-28-cvxpylayers/
CVXPY creates powerful new PyTorch and TensorFlow layers
https://locuslab.github.io/2019-10-28-cvxpylayers/
locuslab.github.io
Differentiable Convex Optimization Layers
CVXPY creates powerful new PyTorch and TensorFlow layers