There are now many state-of-the-art computer vision algorithms which are a git clone away. We found that existing systems for distributed data analysis were not well suited to dealing with the computational challenges of applying computer vision algorithms to terabyte or petabyte sized video collections, so we designed and built a system called Scanner to make efficient video analysis easier.
Source: cmu.edu
One of the most complex and performance critical parts of any machine learning framework is its support for device specific acceleration. Indeed, without efficient GPU acceleration, much of modern ML research and deployment would not be possible. This acceleration support is also a critical bottleneck, both in terms of adding support for a wider range of hardware targets (including mobile) as well as for writing new research kernels.
Read More
Nengo is a graphical and scripting based Python package for simulating large-scale neural networks. Nengo can create sophisticated spiking or non-spiking neural simulations with sensible defaults in a few lines of code. Yet, Nengo is highly extensible and flexible.
Read More