Image
Fredo Durand and Sam Madden
MIT news article

The MIT Stephen A. Schwarzman College of Computing announced its first two named professorships, beginning July 1, to Frédo Durand and Samuel Madden in the Department of Electrical Engineering and Computer Science (EECS). These named positions recognize the outstanding achievements and future potential of their academic careers.

work of the future
Work of the Future Event of the Year
The 4th annual Congress was a virtual event that featured the final report from the MIT Task Force on the Work of the Future. Hosted by MIT's Task Force on Work of the Future, CSAIL, and Initiative on the Digital Economy, this year's Congress highlighted research findings from the MIT Task Force on Work of the Future's final report released in November 2020. Given the rapidly changing environment brought on by Covid-19, this topic is more important and relevant than ever.
Image
AI music gestures
MIT news article

A new artificial intelligence tool developed by the MIT-IBM Watson AI Lab leverages the virtual eyes and ears of a computer to separate similar sounds that are tricky even for humans to differentiate. The tool improves on earlier iterations by matching the movements of individual musicians, via their skeletal keypoints, to the tempo of individual parts, allowing listeners to isolate a single flute or violin among multiple flutes or violins. 

Category
Graphic & Vision
Language
Python

This repository contains the demo code for the CVPR'17 paper Network Dissection: Quantifying Interpretability of Deep Visual Representations. You can use this code with naive Caffe, with matcaffe and pycaffe compiled. We also provide a PyTorch wrapper to apply NetDissect to probe networks in PyTorch format.

MIT License
Last Updated
computer vision
July 6-10, 2020

Registration Deadline: June 22, 2020. This course covers the latest developments in vision AI, with a sharp focus on advanced deep learning methods, specifically convolutional neural networks, that enable smart vision systems to recognize, reason, interpret and react to images with improved precision.

Member DiscountAlliances members are eligible for a discount for this program. Please log in to view discount instructions.
Category
Graphic & Vision
Language
Python

GAN Dissection is a way to inspect the internal representations of a generative adversarial network (GAN) to understand how internal units align with human-interpretable concepts. It is part of NetDissect.

MIT License
Last Updated