Deep Learning in Healthcare and Computational Biology
Tangible and Practical Deep Learning Projects Repository for Healthcare such as Cancer, Drug Discovery, Genomic and More
https://github.com/TarrySingh/Deep-Neural-Networks-HealthCare
Tangible and Practical Deep Learning Projects Repository for Healthcare such as Cancer, Drug Discovery, Genomic and More
https://github.com/TarrySingh/Deep-Neural-Networks-HealthCare
An outstanding Nature Medicine
guide to deep learning in healthcare, including computer vision, natural language processing, reinforcement learning, and generalized methods in genomic medicine and beyond. https://www.nature.com/articles/s41591-018-0316-z
guide to deep learning in healthcare, including computer vision, natural language processing, reinforcement learning, and generalized methods in genomic medicine and beyond. https://www.nature.com/articles/s41591-018-0316-z
Nature
A guide to deep learning in healthcare
Nature Medicine - A primer for deep-learning techniques for healthcare, centering on deep learning in computer vision, natural language processing, reinforcement learning, and generalized methods.
ArtificialIntelligenceArticles
https://www.ted.com/talks/sebastian_thrun_and_chris_anderson_the_new_generation_of_computers_is_programming_itself/transcript#t-1407330
cs.stanford.edu
Skin cancer classification with deep learning
Deep learning matches the performance of dermatologists at skin cancer classification.
Uber’s EvoGrad is a dev library for evolutionary algorithms
Blog by Kyle Wiggers: https://venturebeat.com/2019/07/22/ubers-evograd-is-a-dev-library-for-evolutionary-algorithms/
#EvolutionaryAlgorithms #NaturalEvolutionStrategies #Python
Blog by Kyle Wiggers: https://venturebeat.com/2019/07/22/ubers-evograd-is-a-dev-library-for-evolutionary-algorithms/
#EvolutionaryAlgorithms #NaturalEvolutionStrategies #Python
VentureBeat
Uber’s EvoGrad is a dev library for evolutionary algorithms
Uber's EvoGrad is a development library for evolutionary machine learning algorithms. It's freely available on GitHub.
Dynamical Distance Learning for Unsupervised and Semi-Supervised Skill Discovery
Hartikainen et al.: https://arxiv.org/abs/1907.08225
#ArtificialIntelligence #Robotics #MachineLearning
Hartikainen et al.: https://arxiv.org/abs/1907.08225
#ArtificialIntelligence #Robotics #MachineLearning
arXiv.org
Dynamical Distance Learning for Semi-Supervised and Unsupervised...
Reinforcement learning requires manual specification of a reward function to learn a task. While in principle this reward function only needs to specify the task goal, in practice reinforcement...
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
Bosselut et al.: https://arxiv.org/abs/1906.05317
#ArtificialIntelligence #DeepLearning #MachineLearning
Bosselut et al.: https://arxiv.org/abs/1906.05317
#ArtificialIntelligence #DeepLearning #MachineLearning
arXiv.org
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017)....
"Predicting planets from orbital perturbations using deep learning"
Blog post by Kyle A. Pearson: https://medium.com/tensorflow/predicting-planets-from-orbital-perturbations-using-deep-learning-cb58fb9996c5
#Astronomy #TensorFlow #DeepLearning
Blog post by Kyle A. Pearson: https://medium.com/tensorflow/predicting-planets-from-orbital-perturbations-using-deep-learning-cb58fb9996c5
#Astronomy #TensorFlow #DeepLearning
Medium
Predicting planets from orbital perturbations using deep learning
A guest post by Kyle A. Pearson
"The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities"
By Lehman, Clune, Misevic et al.: https://arxiv.org/pdf/1803.03453.pdf
#ArtificialLife #DigitalEvolution #EvolutionStrategy
By Lehman, Clune, Misevic et al.: https://arxiv.org/pdf/1803.03453.pdf
#ArtificialLife #DigitalEvolution #EvolutionStrategy
"Visualizing and Measuring the Geometry of BERT"
Coenen et al.: https://arxiv.org/abs/1906.02715
Blog post : https://pair-code.github.io/interpretability/bert-tree/
#ArtificialIntelligence #DeepLearning #MachineLearning
Coenen et al.: https://arxiv.org/abs/1906.02715
Blog post : https://pair-code.github.io/interpretability/bert-tree/
#ArtificialIntelligence #DeepLearning #MachineLearning
arXiv.org
Visualizing and Measuring the Geometry of BERT
Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks...
"Learning to Traverse Latent Spaces for Musical Score Inpainting"
Pati et al.: https://arxiv.org/abs/1907.01164
GitHub: https://github.com/ashispati/InpaintNet
Demo: https://ashispati.github.io/inpaintnet/
#ArtificialIntelligence #MachineLearning #Music
Pati et al.: https://arxiv.org/abs/1907.01164
GitHub: https://github.com/ashispati/InpaintNet
Demo: https://ashispati.github.io/inpaintnet/
#ArtificialIntelligence #MachineLearning #Music
arXiv.org
Learning to Traverse Latent Spaces for Musical Score Inpainting
Music Inpainting is the task of filling in missing or lost information in a piece of music. We investigate this task from an interactive music creation perspective. To this end, a novel deep...
Everything You Need to Know About Autoencoders in TensorFlow
https://towardsdatascience.com/everything-you-need-to-know-about-autoencoders-in-tensorflow-b6a63e8255f0
https://towardsdatascience.com/everything-you-need-to-know-about-autoencoders-in-tensorflow-b6a63e8255f0
Medium
Everything You Need to Know About Autoencoders in TensorFlow
From theory to implementation in TensorFlow
"Behind the Selection of the NeurIPS 2019 Workshops"
By Neural Information Processing Systems Conference: https://medium.com/@NeurIPSConf/2019workshops-ec820e4d558e
#MachineLearning #Neurips2019 #DeepLearning #ReinforcementLearning #Neurips
By Neural Information Processing Systems Conference: https://medium.com/@NeurIPSConf/2019workshops-ec820e4d558e
#MachineLearning #Neurips2019 #DeepLearning #ReinforcementLearning #Neurips
Medium
Behind the Selection of the NeurIPS 2019 Workshops
NeurIPS 2019 workshop decisions just went out! Read on to hear all about the review process and see a preliminary list of workshops.
Let’s code a Neural Network in plain NumPy
Blog by Piotr Skalski: https://towardsdatascience.com/lets-code-a-neural-network-in-plain-numpy-ae7e74410795
#artificialintelligence #neuralnetwork #numpy
@ArtificialIntelligenceArticles
Blog by Piotr Skalski: https://towardsdatascience.com/lets-code-a-neural-network-in-plain-numpy-ae7e74410795
#artificialintelligence #neuralnetwork #numpy
@ArtificialIntelligenceArticles
Medium
Let’s code a Neural Network in plain NumPy
Mysteries of Neural Networks Part III
Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
https://arxiv.org/abs/1907.07587v1
https://arxiv.org/abs/1907.07587v1
arXiv.org
Zygote: A Differentiable Programming System to Bridge Machine...
Scientific computing is increasingly incorporating the advancements in
machine learning and the ability to work with large amounts of data. At the
same time, machine learning models are becoming...
machine learning and the ability to work with large amounts of data. At the
same time, machine learning models are becoming...
Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning. arxiv.org/abs/1907.08070
"Rules-of-thumb for building a Neural Network"
Blog by Chitta Ranjan : https://towardsdatascience.com/17-rules-of-thumb-for-building-a-neural-network-93356f9930af
#MachineLearning #NeuralNetwork #TensorFlow
Blog by Chitta Ranjan : https://towardsdatascience.com/17-rules-of-thumb-for-building-a-neural-network-93356f9930af
#MachineLearning #NeuralNetwork #TensorFlow
Medium
Rules-of-thumb for building a Neural Network
In this article, we will get a starting point to build an initial Neural Network. We will learn the thumb-rules, e.g. the number of hidden…
Open-Source RL List
All major model-free RL algorithms https://docs.google.com/spreadsheets/d/1EeFPd-XIQ3mq_9snTlAZSsFY7Hbnmd7P5bbT8LPuMn0/edit#gid=0
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
All major model-free RL algorithms https://docs.google.com/spreadsheets/d/1EeFPd-XIQ3mq_9snTlAZSsFY7Hbnmd7P5bbT8LPuMn0/edit#gid=0
#ArtificialIntelligence #DeepLearning #ReinforcementLearning
Google Docs
Open-source RL
Wow 😲 , Lyft just open sourced its autonomous driving dataset from its Level 5 self-driving fleet!
Download: https://level5.lyft.com/dataset/
___________________________________________
For reference, the Lyft Level 5 Dataset includes:
1) Over 55,000 human-labeled 3D annotated frames;
2) Data from 7 cameras and up to 3 lidars;
3) A drivable surface map; and,
4) An underlying HD spatial semantic map (including lanes, crosswalks, etc.)
___________________________________________
Download: https://level5.lyft.com/dataset/
___________________________________________
For reference, the Lyft Level 5 Dataset includes:
1) Over 55,000 human-labeled 3D annotated frames;
2) Data from 7 cameras and up to 3 lidars;
3) A drivable surface map; and,
4) An underlying HD spatial semantic map (including lanes, crosswalks, etc.)
___________________________________________