Unsupervised Separation of Dynamics from Pixels
Silvia Chiappa and Ulrich Paquet : https://arxiv.org/abs/1907.12906
#DeepLearning #MachineLearning #UnsupervisedLearning
Silvia Chiappa and Ulrich Paquet : https://arxiv.org/abs/1907.12906
#DeepLearning #MachineLearning #UnsupervisedLearning
arXiv.org
Unsupervised Separation of Dynamics from Pixels
We present an approach to learn the dynamics of multiple objects from image
sequences in an unsupervised way. We introduce a probabilistic model that first
generate noisy positions for each object...
sequences in an unsupervised way. We introduce a probabilistic model that first
generate noisy positions for each object...
Dopamine: A Research Framework for Deep Reinforcement Learning
Pablo Samuel Castro, Subhodeep Moitra, Carles Gelada, Saurabh Kumar and Marc G. Bellemare: https://arxiv.org/abs/1812.06110
Code: https://github.com/google/dopamine
#deeplearning #reinforcementlearning #tensorflow
Pablo Samuel Castro, Subhodeep Moitra, Carles Gelada, Saurabh Kumar and Marc G. Bellemare: https://arxiv.org/abs/1812.06110
Code: https://github.com/google/dopamine
#deeplearning #reinforcementlearning #tensorflow
arXiv.org
Dopamine: A Research Framework for Deep Reinforcement Learning
Deep reinforcement learning (deep RL) research has grown significantly in recent years. A number of software offerings now exist that provide stable, comprehensive implementations for...
"Long Short-Term-Memory"
Sepp Hochreiter and Jürgen Schmidhuber : https://www.bioinf.jku.at/publications/older/2604.pdf
#ArtificialIntelligence #LongShortTermMemory #LSTM
Sepp Hochreiter and Jürgen Schmidhuber : https://www.bioinf.jku.at/publications/older/2604.pdf
#ArtificialIntelligence #LongShortTermMemory #LSTM
Adversarial Examples Are Not Bugs, They Are Features
Ilyas et al.: https://arxiv.org/abs/1905.02175
#MachineLearning #Cryptography #Security
Ilyas et al.: https://arxiv.org/abs/1905.02175
#MachineLearning #Cryptography #Security
arXiv.org
Adversarial Examples Are Not Bugs, They Are Features
Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial examples can be...
TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfer
Allevato et al.: https://arxiv.org/abs/1907.11200
#ArtificialIntelligence #MachineLearning #Robotics
Allevato et al.: https://arxiv.org/abs/1907.11200
#ArtificialIntelligence #MachineLearning #Robotics
arXiv.org
TuneNet: One-Shot Residual Tuning for System Identification and...
As researchers teach robots to perform more and more complex tasks, the need for realistic simulation environments is growing. Existing techniques for closing the reality gap by approximating...
Why Real Neurons Learn Faster
A closer look into differences between natural nervous systems & artificial #NeuralNetworks
https://www.codeproject.com/Articles/1275031/Why-Real-Neurons-Learn-Faster
A closer look into differences between natural nervous systems & artificial #NeuralNetworks
https://www.codeproject.com/Articles/1275031/Why-Real-Neurons-Learn-Faster
Codeproject
Why Real Neurons Learn Faster
A closer look into differences between natural nervous systems and artificial neural networks
ArtificialIntelligenceArticles
https://www.mousemotorlab.org/deeplabcut
DeepLabCut – markerless pose estimation of user-defined features with DL for all animals, including humans
By DeepLabCut and trackingplumes
Project
https://www.mousemotorlab.org/deeplabcut
Github
https://github.com/AlexEMG/DeepLabCut
By DeepLabCut and trackingplumes
Project
https://www.mousemotorlab.org/deeplabcut
Github
https://github.com/AlexEMG/DeepLabCut
The Mathis Lab of Adaptive Intelligence
DeepLabCut — The Mathis Lab of Adaptive Intelligence
Adaloss: Adaptive Loss Function for Landmark Localization. arxiv.org/abs/1908.01070
Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration. arxiv.org/abs/1908.01010
Improving Deep Reinforcement Learning in Minecraft with Action Advice. ) arxiv.org/abs/1908.01007
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
Talman et al.: https://arxiv.org/abs/1908.02262
GitHub: https://github.com/Helsinki-NLP/prosody
#dataset #machinelearning #naturallanguageprocessing
Talman et al.: https://arxiv.org/abs/1908.02262
GitHub: https://github.com/Helsinki-NLP/prosody
#dataset #machinelearning #naturallanguageprocessing
arXiv.org
Predicting Prosodic Prominence from Text with Pre-trained...
In this paper we introduce a new natural language processing dataset and
benchmark for predicting prosodic prominence from written text. To our
knowledge this will be the largest publicly...
benchmark for predicting prosodic prominence from written text. To our
knowledge this will be the largest publicly...
Structured Knowledge Discovery from Massive Text Corpus. arxiv.org/abs/1908.01837
Risk Management via Anomaly Circumvent: Mnemonic Deep Learning for Midterm Stock Prediction. arxiv.org/abs/1908.01112
Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain Shift arxiv.org/abs/1908.01098
U-Net Fixed-Point Quantization for Medical Image Segmentation. arxiv.org/abs/1908.01073