Machine Learning Holographic Mapping by Neural Network Renormalization Group
Hu et al.: https://arxiv.org/abs/1903.00804
#ArtificialIntelligence #NeuralNetworks #MachineLearning #StatisticalMechanics #Physics
Hu et al.: https://arxiv.org/abs/1903.00804
#ArtificialIntelligence #NeuralNetworks #MachineLearning #StatisticalMechanics #Physics
Speech and Language Processing (3rd ed. draft)
Dan Jurafsky and James H. Martin
https://web.stanford.edu/~jurafsky/slp3/
#BOOK
Dan Jurafsky and James H. Martin
https://web.stanford.edu/~jurafsky/slp3/
#BOOK
The new method is far faster and more efficient than previous methods
https://edgy.app/deep-learning-planet-masses
https://edgy.app/deep-learning-planet-masses
Diabetic retinopathy screening can only be done by specialists. Diabetic retinopathy is a complication affecting one in three people with diabetes. Without early detection and timely treatment, it can lead to partial loss of vision or blindness. Trial shows GP (general practitioner) screenings with technology as effective as a specialist.
https://www.csiro.au/en/Research/BF/Areas/Digital-health/Improving-access/Diabetic-retinopathy
https://www.csiro.au/en/Research/BF/Areas/Digital-health/Improving-access/Diabetic-retinopathy
www.csiro.au
Improving eye screening for people with diabetes using AI
We've developed and trialled new technology to enable GPs to screen for diabetic retinopathy, helping save the eyesight of people with diabetes.
This is important.
https://www.technologynetworks.com/neuroscience/news/how-synaptic-learning-depends-on-deep-brain-feedback-313436
https://www.technologynetworks.com/neuroscience/news/how-synaptic-learning-depends-on-deep-brain-feedback-313436
Neuroscience from Technology Networks
How Synaptic Learning Depends on Deep Brain Feedback
UNIGE scientists uncover the role of synaptic feedback systems in shaping learning processes in the brain’s cortex – a discovery that may prove valuable for developing efficient artificial intelligence.
Supervised learning with quantum-enhanced feature spaces
- Vojtěch Havlíček et. al.
Nature Version:
https://www.nature.com/articles/s41586-019-0980-2
Free Access:
https://arxiv.org/pdf/1804.11326
- Vojtěch Havlíček et. al.
Nature Version:
https://www.nature.com/articles/s41586-019-0980-2
Free Access:
https://arxiv.org/pdf/1804.11326
Google’s dataset search: https://toolbox.google.com/datasetsearch
#dataset #artificialintelligence #datasets #deeplearning #machinelearning
#dataset #artificialintelligence #datasets #deeplearning #machinelearning
Deep Learning Drizzle
"Read enough so you start developing intuitions and then trust your intuitions and go for it!" - Geoffrey Hinton
https://deep-learning-drizzle.github.io/
#artificialintelligence #deeplearning #machinelearning
"Read enough so you start developing intuitions and then trust your intuitions and go for it!" - Geoffrey Hinton
https://deep-learning-drizzle.github.io/
#artificialintelligence #deeplearning #machinelearning
The Neural Aesthetic
Notes and around 30 hours of video lectures, by Gene Kogan: https://ml4a.github.io/classes/itp-F18/
#art #artificialintelligence #deeplearning #generativeadversarialnetworks
Notes and around 30 hours of video lectures, by Gene Kogan: https://ml4a.github.io/classes/itp-F18/
#art #artificialintelligence #deeplearning #generativeadversarialnetworks
Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
By K. Kandasamy et al.: https://www.cs.cmu.edu/~kkandasa/docs/proposal.pdf
Python Library: https://github.com/dragonfly/dragonfly/
Docs: https://dragonfly-opt.readthedocs.io/en/master/
#ArtificialIntelligence #DeepLearning #MachineLearning
By K. Kandasamy et al.: https://www.cs.cmu.edu/~kkandasa/docs/proposal.pdf
Python Library: https://github.com/dragonfly/dragonfly/
Docs: https://dragonfly-opt.readthedocs.io/en/master/
#ArtificialIntelligence #DeepLearning #MachineLearning
Tracking Progress in Natural Language Processing
By Sebastian Ruder: https://github.com/sebastianruder/NLP-progress
#deeplearning #machinelearning #naturallanguageprocessing
By Sebastian Ruder: https://github.com/sebastianruder/NLP-progress
#deeplearning #machinelearning #naturallanguageprocessing
Semantic Image Synthesis with Spatially-Adaptive Normalization”
Park et al.: https://nvlabs.github.io/SPADE/
#artificialintelligence #deeplearning #generativedesign
Park et al.: https://nvlabs.github.io/SPADE/
#artificialintelligence #deeplearning #generativedesign
nvlabs.github.io
Semantic Image Synthesis with Spatially-Adaptive Normalization
Reinforcement Learning for Improving Agent Design"
By David Ha
Blog: https://designrl.github.io
Paper: https://arxiv.org/abs/1810.03779
Code: https://github.com/hardmaru/astool/
#ReinforcementLearning
#MachineLearning #Design
By David Ha
Blog: https://designrl.github.io
Paper: https://arxiv.org/abs/1810.03779
Code: https://github.com/hardmaru/astool/
#ReinforcementLearning
#MachineLearning #Design
RL for Improving Agent Design
What happens when we let an agent learn a better body design?
Seven Myths in Machine Learning Research
https://crazyoscarchang.github.io/
https://crazyoscarchang.github.io/
Neighbourhood Consensus Networks
Rocco et al.: https://arxiv.org/abs/1810.10510
#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #nips2018
Rocco et al.: https://arxiv.org/abs/1810.10510
#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #nips2018