Archives for Carnegie Mellon University

14 Jun

Can MXNet Stand Up To TensorFlow & PyTorch?

image-23536
image-23536

“MXNet, born and bred here at CMU, is the most scalable framework for deep learning I have seen and is a great example of what makes this area of computer science so beautiful – that you have different disciplines which all work so well together: imaginative linear algebra working in a novel way with massive…

The post Can MXNet Stand Up To TensorFlow & PyTorch? appeared first on Analytics India Magazine.

08 Feb

Carnegie Researchers Use AI To Review Scientific Papers

image-19858
image-19858

Every year, the machine learning community is treated to at least half a dozen international conferences flaunting exceptional research from across the world. The not so attractive aspect of these conferences is the review system for the researchers whose credentials and careers are intrinsically linked to the acceptance at these conferences. Every year, a handful…

The post Carnegie Researchers Use AI To Review Scientific Papers appeared first on Analytics India Magazine.

20 Oct

Researchers Combine AI & Quantum Mechanics To Solve Renewable Energy Storage Problems

image-16929
image-16929

“Researchers are developing AI that will accurately predict atomic interactions faster than the compute-heavy simulations of today.” The sun doesn’t always shine and to store energy[batteries] in its absence is a costly affair. So, with all this talk about going green, how is it possible to incentivise people towards futuristic yet unsustainable and expensive goals? …

The post Researchers Combine AI & Quantum Mechanics To Solve Renewable Energy Storage Problems appeared first on Analytics India Magazine.

20 Oct

Researchers Combine AI & Quantum Mechanics To Solve Renewable Energy Storage Problems

image-16931
image-16931

“Researchers are developing AI that will accurately predict atomic interactions faster than the compute-heavy simulations of today.” The sun doesn’t always shine and to store energy[batteries] in its absence is a costly affair. So, with all this talk about going green, how is it possible to incentivise people towards futuristic yet unsustainable and expensive goals? …

The post Researchers Combine AI & Quantum Mechanics To Solve Renewable Energy Storage Problems appeared first on Analytics India Magazine.

25 Jul

What Is Weight Sharing In Deep Learning And Why Is It Important

image-14300
image-14300

Neural architecture search (NAS) deals with the selection of neural models for specific learning problems. NAS, however, is computationally expensive for automating and democratising machine learning. The initial success of NAS was attributed partially to the weight-sharing method, which helped in the dramatic acceleration of probing the architectures. But why is the weight sharing method…

The post What Is Weight Sharing In Deep Learning And Why Is It Important appeared first on Analytics India Magazine.