TF Dev Summit: Google Debuts TensorFlow 2.0 Alpha
TensorFlow is the world’s most popular open source machine learning library. Since its initial release in 2015, the Google Brain product has been downloaded over 41 million times. At this week’s 2019 TensorFlow Dev Summit, Google announced a major upgrade on the framework, the TensorFlow 2.0 Alpha version.
TF Dev Summit: Google launches TensorFlow Lite 1.0 for Mobile and Embedded Devices
Google today introduced TensorFlow Lite 1.0, its framework for developers deploying AI models on mobile and IoT devices. Improvements include selective registration and quantization during and after training for faster, smaller models. Quantization has led to 4 times compression of some models.
TF Dev Summit: Introducing TensorFlow Federated
TensorFlow Federated (TFF) is an open source framework for experimenting with machine learning and other computations on decentralized data. It implements an approach called Federated Learning (FL), which enables many participating clients to train shared ML models, while keeping their data locally.
Google Open-Sources GPipe Library for Training Large-Scale Neural Network Models
Deep neural network (DNN) models have demonstrated that larger DNN models produce better task performance. These huge models are however becoming increasingly difficult to train. Google this week introduced GPipe, an open-source library that dramatically improves training efficacy for large-scale neural network models.
(Synced) / (Google Brain) / (GitHub)
Google Brain: High-Fidelity Image Generation With Fewer Labels
In this work researchers demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform state-ofthe-art (SOTA) on both unsupervised ImageNet synthesis, as well as in the conditional setting.
(Google Brain & DeepMind & ETH Zurich) / (GitHub)
Introducing Activation Atlases
We’ve created activation atlases (in collaboration with Google researchers), a new technique for visualizing what interactions between neurons can represent. As AI systems are deployed in increasingly sensitive contexts, having a better understanding of their internal decision-making processes will let us identify weaknesses and investigate failures.
CVPR 2019 | Triple ‘Strong Accept’ for CVPR 2019: Reinforced Cross-Modal Matching & Self-Supervised Imitation Learning for Vision-Language Navigation
A total of 1300 papers were accepted from a record-high 5165 submissions this year, and one standout already garnering attention is Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation. The paper is said to have received all three “Strong Accepts” in the peer review and ranks №1.
(Synced) / (UCSB & Microsoft & Duke)
CVPR 2019 | Neural Task Graphs: Generalizing to Unseen Tasks from A Single Video Demonstration
Learning sequential decisions and adapting to new task objectives at test time is a long-standing challenge in AI. In rich real domains, an autonomous agent has to acquire new skills with minimal supervision. In this work, researchers push a step further to address one-shot visual imitation learning that operates directly on videos.
You May Also Like
ICLR 2019 | ‘Fast as Adam & Good as SGD’ — New Optimizer Has Both
A paper recently accepted for ICLR 2019 challenges this with a novel optimizer — AdaBound — that authors say can train machine learning models “as fast as Adam and as good as SGD.” Basically, AdaBound is an Adam variant that employs dynamic bounds on learning rates to achieve a gradual and smooth transition to SGD.
NeurIPS 2019 Dates And Details Announced
The organizers of NeurIPS (Conference on Neural Information Processing Systems) today announced the dates and other information regarding NeurIPS 2019. The world’s most prestigious machine learning conference will be held Sunday December 8 through Saturday December 14 at the Vancouver Convention Center.
Global AI Events
March 11~12, Conversational Interaction Conference San Jose, United States
March 12~13, AI Tech World London, United Kingdom
March 17~20, ACM IUI Los Angeles, United States
Global AI Opportunities