Minkowski Engine
The Minkowski Engine is an auto-diff library for generalized sparse convolutions and high-dimensional sparse tensors https://github.com/StanfordVL/MinkowskiEngine
#artificialintelligence #deeplearning #machinelearning #spacetime
The Minkowski Engine is an auto-diff library for generalized sparse convolutions and high-dimensional sparse tensors https://github.com/StanfordVL/MinkowskiEngine
#artificialintelligence #deeplearning #machinelearning #spacetime
GitHub
GitHub - NVIDIA/MinkowskiEngine: Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors - NVIDIA/MinkowskiEngine
"Importance Weighted Hierarchical Variational Inference"
By Artem Sobolev and Dmitry Vetrov: https://arxiv.org/abs/1905.03290
Talk: https://youtu.be/pdSu7XfGhHw
#Bayesian #MachineLearning #VariationalInference
By Artem Sobolev and Dmitry Vetrov: https://arxiv.org/abs/1905.03290
Talk: https://youtu.be/pdSu7XfGhHw
#Bayesian #MachineLearning #VariationalInference
MineRL Competition 2019
Competition Overview: https://minerl.io/competition/
#artificialintelligence #deeplearning #reinforcementlearning #research #technology
Competition Overview: https://minerl.io/competition/
#artificialintelligence #deeplearning #reinforcementlearning #research #technology
Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks
Schmidt et al.: https://arxiv.org/abs/1905.03709
#ComputerVision #PatternRecognition #ArtificialIntelligence
Schmidt et al.: https://arxiv.org/abs/1905.03709
#ComputerVision #PatternRecognition #ArtificialIntelligence
arXiv.org
Visualizing the Consequences of Climate Change Using...
We present a project that aims to generate images that depict accurate, vivid, and personalized outcomes of climate change using Cycle-Consistent Adversarial Networks (CycleGANs). By training our...
"Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups"
By Thomas Wolf: https://medium.com/huggingface/training-larger-batches-practical-tips-on-1-gpu-multi-gpu-distributed-setups-ec88c3e51255
#ArtificialInteligence #DeepLearning #MachineLearning #NeuralNetworks #Research
By Thomas Wolf: https://medium.com/huggingface/training-larger-batches-practical-tips-on-1-gpu-multi-gpu-distributed-setups-ec88c3e51255
#ArtificialInteligence #DeepLearning #MachineLearning #NeuralNetworks #Research
Medium
💥 Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups
Training neural networks with larger batches in PyTorch: gradient accumulation, gradient checkpointing, multi-GPUs and distributed setups…
An Empirical Study of Example Forgetting During Deep Neural Network Learning
Joint work with Alessandro Sordoni, Remi Tachet, Adam Trischler, Yoshua Bengio, and Geoff Gordon
Paper: https://bit.ly/2H8yQUg
Code: https://bit.ly/2vMH6mw
#ICLR #ICLR2019 #MachineLearning
Joint work with Alessandro Sordoni, Remi Tachet, Adam Trischler, Yoshua Bengio, and Geoff Gordon
Paper: https://bit.ly/2H8yQUg
Code: https://bit.ly/2vMH6mw
#ICLR #ICLR2019 #MachineLearning
GitHub
mtoneva/example_forgetting
Contribute to mtoneva/example_forgetting development by creating an account on GitHub.
Learning higher-order sequential structure with cloned HMMs
Dedieu et al.: https://arxiv.org/abs/1905.00507
#ArtificialIntelligence #MachineLearning #Technology
Dedieu et al.: https://arxiv.org/abs/1905.00507
#ArtificialIntelligence #MachineLearning #Technology
arXiv.org
Learning higher-order sequential structure with cloned HMMs
Variable order sequence modeling is an important problem in artificial and natural intelligence. While overcomplete Hidden Markov Models (HMMs), in theory, have the capacity to represent long-term...
Unified Language Model Pre-training for Natural Language Understanding and Generation
Dong et al.: https://arxiv.org/abs/1905.03197v1
#ArtificialIntelligence #DeepLearning #MachineLearning
Dong et al.: https://arxiv.org/abs/1905.03197v1
#ArtificialIntelligence #DeepLearning #MachineLearning
arXiv.org
Unified Language Model Pre-training for Natural Language...
This paper presents a new Unified pre-trained Language Model (UniLM) that can
be fine-tuned for both natural language understanding and generation tasks. The
model is pre-trained using three types...
be fine-tuned for both natural language understanding and generation tasks. The
model is pre-trained using three types...
A machine learning algorithm can detect signs of anxiety and depression in the speech patterns of young children, potentially providing a fast and easy way of diagnosing conditions that are difficult to spot and often overlooked in young people, according to new research.
https://www.technologynetworks.com/neuroscience/news/ai-can-detect-depression-in-a-childs-speech-319040
https://www.technologynetworks.com/neuroscience/news/ai-can-detect-depression-in-a-childs-speech-319040
Technology Networks
AI Can Detect Depression in a Child's Speech
A machine learning algorithm can detect signs of anxiety and depression in the speech patterns of young children, potentially providing a fast and easy way of diagnosing conditions that are difficult to spot and often overlooked in young people, according…
"The Roles of Supervised Machine Learning in Systems Neuroscience" https://arxiv.org/abs/1805.08239
arXiv.org
The Roles of Supervised Machine Learning in Systems Neuroscience
Over the last several years, the use of machine learning (ML) in neuroscience has been rapidly increasing. Here, we review ML's contributions, both realized and potential, across several areas of...
"Evolving Images for Visual Neurons Using a Deep Generative Network Reveals Coding Principles and Neuronal Preferences"
https://www.cell.com/action/showPdf?pii=S0092-8674%2819%2930391-5
https://www.cell.com/action/showPdf?pii=S0092-8674%2819%2930391-5
"AI Can Detect Alzheimer’s Disease in Brain Scans Six Years Before a Diagnosis"
News article: https://www.ucsf.edu/news/2018/12/412946/artificial-intelligence-can-detect-alzheimers-disease-brain-scans-six-years
Research article: https://www.ehidc.org/sites/default/files/resources/files/A%20Deep%20Learning%20Model%20to%20Predict%20a%20Diagnosis%20of%20Alzheimer%20Disease.pdf
News article: https://www.ucsf.edu/news/2018/12/412946/artificial-intelligence-can-detect-alzheimers-disease-brain-scans-six-years
Research article: https://www.ehidc.org/sites/default/files/resources/files/A%20Deep%20Learning%20Model%20to%20Predict%20a%20Diagnosis%20of%20Alzheimer%20Disease.pdf
Artificial Intelligence Can Detect Alzheimer’s Disease in Brain Scans Six Years Before a Diagnosis | UC San Francisco
AI Could Catch Alzheimer’s in Brain Scans 6 Years Earlier
Researchers programmed a machine-learning algorithm to diagnose early-stage Alzheimer’s disease from a very common type of brain scan.
A new study using machine learning has identified brain-based dimensions of mental health disorders, an advance towards much-needed biomarkers to more accurately diagnose and treat patients.
The research is in Nature Communications. (full open access)
https://neurosciencenews.com/machine-learning-brain-networks-mental-health-9650/
The research is in Nature Communications. (full open access)
https://neurosciencenews.com/machine-learning-brain-networks-mental-health-9650/
Neuroscience News
Machine Learning Links Dimensions of Mental Illness to Brain Network Abnormalities
Researchers use machine learning technology to identify brain based dimensions of mental health disorders.
“Godfather of Deep Learning” geoffreyhinton
“We humans are neural nets. What we can do, machines can do”
Peak Hubris. "Smashing the territory with the map".
https://syncedreview.com/2019/05/10/google-i-o-2019-geoffrey-hinton-says-machines-can-do-anything-humans-can/
“We humans are neural nets. What we can do, machines can do”
Peak Hubris. "Smashing the territory with the map".
https://syncedreview.com/2019/05/10/google-i-o-2019-geoffrey-hinton-says-machines-can-do-anything-humans-can/
Synced
Google I/O 2019 | Geoffrey Hinton Says Machines Can Do Anything Humans Can
Artificial intelligence is closing the gap on humans. Machines are rapidly honing their skills in object recognition and natural language interaction, and advanced AI agents have already beat human…
PyTorch implementation of the Leap Meta-Learner
GitHub: https://github.com/amzn/metalearn-leap
Paper by Flennerhag et al.: https://arxiv.org/abs/1812.01054
#MachineLearning #ArtificialIntelligence #TransferLearning
GitHub: https://github.com/amzn/metalearn-leap
Paper by Flennerhag et al.: https://arxiv.org/abs/1812.01054
#MachineLearning #ArtificialIntelligence #TransferLearning
GitHub
GitHub - amzn/metalearn-leap: Original PyTorch implementation of the Leap meta-learner (https://arxiv.org/abs/1812.01054) along…
Original PyTorch implementation of the Leap meta-learner (https://arxiv.org/abs/1812.01054) along with code for running the Omniglot experiment presented in the paper. - GitHub - amzn/metalearn-lea...
Learning Loss for Active Learning
Donggeun Yoo and In So Kweon: https://arxiv.org/abs/1905.03677
#ArtificialIntelligence #DeepLearning #NeuralNetworks
Donggeun Yoo and In So Kweon: https://arxiv.org/abs/1905.03677
#ArtificialIntelligence #DeepLearning #NeuralNetworks
arXiv.org
Learning Loss for Active Learning
The performance of deep neural networks improves with more annotated data. The problem is that the budget for annotation is limited. One solution to this is active learning, where a model asks...
A Survey on Neural Architecture Search
Wistuba et al.: https://arxiv.org/abs/1905.01392
#MachineLearning #ComputerVision #EvolutionaryComputing
Wistuba et al.: https://arxiv.org/abs/1905.01392
#MachineLearning #ComputerVision #EvolutionaryComputing
Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting
Sen et al.: https://arxiv.org/abs/1905.03806
#ArtificialIntelligence #DeepLearning #MachineLearning
Sen et al.: https://arxiv.org/abs/1905.03806
#ArtificialIntelligence #DeepLearning #MachineLearning