Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
http://ai.googleblog.com/2019/05/moving-camera-moving-people-deep.html
http://ai.googleblog.com/2019/05/moving-camera-moving-people-deep.html
research.google
Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
Posted by Tali Dekel, Research Scientist and Forrester Cole, Software Engineer, Machine Perception The human visual system has a remarkable abili...
Getting to Know You: Designing Trustworthy Artificial Personalities
https://medium.designit.com/getting-to-know-you-designing-trustworthy-artificial-personalities-c108bdbbbf83
https://medium.designit.com/getting-to-know-you-designing-trustworthy-artificial-personalities-c108bdbbbf83
Medium
Getting to Know You: Designing Trustworthy Artificial Personalities
Chatbots are here to stay. How can we create task-oriented but not transactional bots?
Deep Learning lecture
The full deck of (600+)
https://glouppe.github.io/info8010-deep-learning/pdf/lec-all.pdf
The full deck of (600+)
https://glouppe.github.io/info8010-deep-learning/pdf/lec-all.pdf
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Article : https://arxiv.org/abs/1905.08233
Video: https://youtu.be/p1b5aiTrGzY
Article : https://arxiv.org/abs/1905.08233
Video: https://youtu.be/p1b5aiTrGzY
Bringing human-like reasoning to driverless car navigation
Autonomous control system “learns” to use simple maps and image data to navigate new, complex routes.
http://news.mit.edu/2019/human-reasoning-ai-driverless-car-navigation-0523
Autonomous control system “learns” to use simple maps and image data to navigate new, complex routes.
http://news.mit.edu/2019/human-reasoning-ai-driverless-car-navigation-0523
MIT News
Bringing human-like reasoning to driverless car navigation
To bring more human-like reasoning to autonomous vehicles, MIT CSAIL researchers created an end-to-end autonomous navigation system that uses only simple maps, like Google Maps, and visual data to enable driverless cars to navigate routes in new, complex…
Privacy-Preserving Obfuscation of Critical Infrastructure Networks
https://arxiv.org/abs/1905.09778
https://arxiv.org/abs/1905.09778
arXiv.org
Privacy-Preserving Obfuscation of Critical Infrastructure Networks
The paper studies how to release data about a critical infrastructure network
(e.g., the power network or a transportation network) without disclosing
sensitive information that can be exploited...
(e.g., the power network or a transportation network) without disclosing
sensitive information that can be exploited...
The ethical automation toolkit
https://towardsdatascience.com/the-ethical-automation-toolkit-f1fd4281534e?source=collection_home---4------2-----------------------
https://towardsdatascience.com/the-ethical-automation-toolkit-f1fd4281534e?source=collection_home---4------2-----------------------
Towards Data Science
The ethical automation toolkit
This toolkit attempts to communicate to nonexperts the deliberations of ethical automation.
Unsupervised Learning with Graph Neural Networks
video: http://www.ipam.ucla.edu/programs/workshops/workshop-iv-deep-geometric-learning-of-big-data-and-applications/?tab=schedule
guide: http://helper.ipam.ucla.edu/publications/glws4/glws4_15546.pdf
video: http://www.ipam.ucla.edu/programs/workshops/workshop-iv-deep-geometric-learning-of-big-data-and-applications/?tab=schedule
guide: http://helper.ipam.ucla.edu/publications/glws4/glws4_15546.pdf
IPAM
Workshop IV: Deep Geometric Learning of Big Data and Applications - IPAM
Tiresias: Predicting Security Events Through Deep Learning
https://arxiv.org/abs/1905.10328
https://arxiv.org/abs/1905.10328
arXiv.org
Tiresias: Predicting Security Events Through Deep Learning
With the increased complexity of modern computer attacks, there is a need for defenders not only to detect malicious activity as it happens, but also to predict the specific steps that will be...
Geoffrey Hinton Leads Google Brain Representation Similarity Index Research Aiming to Understand Neural Networks
https://medium.com/syncedreview/geoffrey-hinton-leads-google-brain-representation-similarity-index-research-aiming-to-understand-b5d14bf77f49
https://medium.com/syncedreview/geoffrey-hinton-leads-google-brain-representation-similarity-index-research-aiming-to-understand-b5d14bf77f49
Medium
Geoffrey Hinton Leads Google Brain Representation Similarity Index Research Aiming to Understand Neural Networks
A Google Brain research team led by Turing Award recipient Geoffrey Hinton recently published a paper that presents an effective method for…
Using Dimensionality Reduction to Visualize Job Polarization
https://towardsdatascience.com/using-dimensionality-reduction-to-visualize-job-polarization-cf2a9ceac90e?source=collection_home---4------1-----------------------
https://towardsdatascience.com/using-dimensionality-reduction-to-visualize-job-polarization-cf2a9ceac90e?source=collection_home---4------1-----------------------
Towards Data Science
Using Dimensionality Reduction to Visualize Job Polarization
In this post, we illustrate how dimensionality reduction techniques including principal component analysis (PCA) and multidimensional…
EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling
http://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html
http://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html
research.google
EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling
Posted by Mingxing Tan, Staff Software Engineer and Quoc V. Le, Principal Scientist, Google AI Convolutional neural networks (CNNs) are commonly de...
Teaching language models grammar really does make them smarter
http://news.mit.edu/2019/teaching-language-models-grammar-makes-them-smarter-0529
http://news.mit.edu/2019/teaching-language-models-grammar-makes-them-smarter-0529
MIT News
Teaching language models grammar really does make them smarter
Researchers have taken psycholinguistic tests originally developed to study human language understanding and adapted them to probe what neural networks know about language. Grammar helps the models learn faster and perform better.
Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
Link: https://arxiv.org/abs/1807.01281
Link: https://arxiv.org/abs/1807.01281
arXiv.org
Human-level performance in first-person multiplayer games with...
Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments and two-player turn-based games. However,...
Using AI to Determine Whether Figurative or Abstract Art is More Popular Today
https://towardsdatascience.com/using-ai-to-determine-whether-figurative-or-abstract-art-is-more-popular-today-401bb18435bf
https://towardsdatascience.com/using-ai-to-determine-whether-figurative-or-abstract-art-is-more-popular-today-401bb18435bf
Medium
Using AI to Determine Whether Figurative or Abstract Art is More Popular Today
Lessons from a Recent Art Fair