Auto-Vectorizing TensorFlow Graphs: Jacobians, Auto-Batching And Beyond

no code implementations • 8 Mar 2019 • Ashish Agarwal, Igor Ganichev

We propose a static loop vectorization optimization on top of high level dataflow IR used by frameworks like TensorFlow.

TensorFlow Eager: A Multi-Stage, Python-Embedded DSL for Machine Learning

1 code implementation • 27 Feb 2019 • Akshay Agrawal, Akshay Naresh Modi, Alexandre Passos, Allen Lavoie, Ashish Agarwal, Asim Shankar, Igor Ganichev, Josh Levenberg, Mingsheng Hong, Rajat Monga, Shanqing Cai

TensorFlow Eager is a multi-stage, Python-embedded domain-specific language for hardware-accelerated machine learning, suitable for both interactive research and production.

BIG-bench Machine Learning

A Dataset and Architecture for Visual Reasoning with a Working Memory

2 code implementations • ECCV 2018 • Guangyu Robert Yang, Igor Ganichev, Xiao-Jing Wang, Jonathon Shlens, David Sussillo

COG is much simpler than the general problem of video analysis, yet it addresses many of the problems relating to visual and logical reasoning and memory -- problems that remain challenging for modern deep learning architectures.

Logical Reasoning Visual Question Answering (VQA) +1