Timeline

  • Compressedheadshot

    Shaan wrote an update.

    Working on redesigning the new ML@B website as internal technologies officer.

  • Last Month

  • 1

    David wrote an update for SongBird.

    Songbird Demo DD1: https://ml.berkeley.edu/dd/songbirddemo.html

  • Crap2

    Naren wrote an update for Wish.

    We are working on designing a Convolutional Neural Network (CNN) to do edge detection and image segmentation so we can better detect blurry images in the foreground.

  • James

    James wrote an update for Non-linear Dynamics Learning via Neural Networks.

    We have been working on testing aDOBO on a toy environment, called Dubins car, where you have to control a car in 3 dimensions to move it to a goal location. We are also working on looking into the efficacy of aDOBO in comparison to model-free approaches. Additionally, we are going to be looking at extending aDOBO to allow for efficient learning of multiple goals. For example, say we wanted to be able to effectively learn how to drive our car not just to one goal location but to any goal location, in a typical model-based RL approach this would be very easy because model-based approaches allow for changing of the cost function without re-learning the dynamics model. However, in the aDOBO framework, we learn the dynamics in a goal-driven way meaning we must re-learn the dynamics whenever we change the cost function, so we are looking into ways to extend aDOBO to avoid this problem.

  • Aaeaaqaaaaaaaau7aaaajdi4ywm4ztkzltdmnjetndi1yi04mtqylwy5ody0mtm4otbkzq

    Kunal wrote an update for Ternary Weight Pruning for SqueezeNet.

    We have been working on building a generalized method to ternary prune a network, and have been working on testing and benchmarking our approach. We have been surprised by the efficiency and power of ternary pruning and through our benchmarks saw a drop in accuracy from 98.16% to 98.07%, with a 16x reduction in model size. We also saw 83% accuracy on ResNet18 on the Cifar10 Dataset, compared to a baseline score of 77% without Ternary Pruning.

  • 11182696 838480836244573 5819473402947223094 o

    Chandan wrote an update.

    We've released our recent work on fMRI connectivity analysis on the ABIDE dataset: Singh, Wang, & Qi, 2017 on arXiv.

  • 11182696 838480836244573 5819473402947223094 o

    Chandan wrote an update.

    We've released our new work on 3D connectome reconstruction: Funke, Tschopp, Grisaitis, Singh, Saalfeld, & Turaga, 2017 on arXiv.

  • 11182696 838480836244573 5819473402947223094 o

    Chandan wrote an update.

    We've published a new paper on the feasibility of interpulse-interval coding: Singh & Levy, 2017.

  • Gefenprofessionalsmall

    Gefen wrote an update.

    Vyrill consulting