MindStorm Session (March 19, 2018)
Session Highlights
-
At the MindStorm session, we started with a discussion about the upcoming hackathon. The hackathon will start on Friday, 27th April 2018 at MindGarage and the results will be announced on Sunday, 29th April 2018 at 12:00 pm EST.
-
Marcus Liwicki shared some insights about the data and how and when the Hackathon will be organized.
-
Some papers were discussed by Kumar Shridhar:
-
Predictive Neural Networks : where the authors showed that linearly activated recurrent neural networks can approximate any time-dependent function f(t) given by a number of function values. The approximation can effectively be learned by simply solving a linear equation system; no backpropagation or similar methods are needed.
-
Adaptive Neural Compilation : where the authors showed that it is possible to compile programs written in a low-level language to a differentiable representation.
-
-
Mendeley Desktop : A very useful application to keep and store all the research papers was discussed by Kumar Shridhar.
-
Finally, the session ended with a topic presentation on ‘Multi Modal learning’ by Saurabh Varshneya.