AI Technology & Industry Review
A research team from Saskatchewan University and Google introduces an innovative unsupervised method for automatic video highlight detection, eliminating the requirements for manual annotations while achieving superior performance compared to previous methods.
In a new paper Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning, a Stanford University research team affirms that simple language skills can emerge in meta-RL agents without direct language supervision by testifying this theory in their customized multi-task environment.
In the new paper Discovering Latent Knowledge in Language Models Without Supervision, a research team from UC Berkeley and Peking University presents Contrast-Consistent Search (CCS), an unsupervised approach for discovering latent knowledge in language models.
A team from UC Berkeley and Facebook AI Research proposes a Neural Manifold Clustering and Embedding (NMCE) method for general-purpose manifold clustering that significantly outperforms autoencoder-based deep subspace clustering approaches.
A research team from OneFlow and Microsoft takes a step toward automatic deep neural network structure design, exploring unsupervised structure-learning and leveraging the efficient coding principle, information theory and computational neuroscience to design structure learning without label information.
A research team from Facebook AI conducts a large-scale study on unsupervised spatiotemporal representation learning from videos. The work takes a unified perspective on four recent image-based frameworks (MoCo, SimCLR, BYOL, SwAV) and investigates a simple objective that can easily generalize unsupervised representation learning methodologies to space-time.
Augmented Temporal Contrast (ATC), a new unsupervised learning (UL) task for learning visual representations agnostic to rewards and without degrading the control policy.
Researchers have proposed a simple but powerful “SimCLR” framework for contrastive learning of visual representations.
Researchers have introduced the first unsupervised learning approach for identifying interpretable semantic directions in the latent space of generative adversarial network (GAN) models.
In 2017 the “Godfather of Deep Learning” Geoffrey Hinton and his students Sara Sabour and Nicholas Frosst proposed the discrimininatively trained, multi-layer capsule system “CapsNet” in their paper Dynamic Routing Between Capsules.
Synced Global AI Weekly May 5th
Facebook AI Chief Yann LeCun introduced his now-famous “cake analogy” at NIPS 2016: “If intelligence is a cake, the bulk of the cake is unsupervised learning, the icing on the cake is supervised learning, and the cherry on the cake is reinforcement learning (RL).”
DataVisor is a Mountain View, California based anti-fraud startup that uses AI to detect fake accounts, prevent money laundering, and protect financial institutions from credit scams. The company offers clients its DataVisor APIs for real-time data connection, and a specialized UI for direct results.
This paper proposes a general approach to achieve “Image-to-Image Translation” by using deep convolutional and conditional generative adversarial networks (GANs).
This paper applies deep learning to a large-scale EHR dataset to extract robust patient descriptors that can be used to predict future patient diseases.
professor Yann LeCun discussed about “predicting under uncertainty: the next frontier in AI” during the lecture at the University of Edinburgh