Behind Every Great Deep Learning Framework Is An Even Greater Programming Languages Concept

​Welcome to this seminar with Erik Meijer,  computer scientist, entrepreneur and professor at Delft University of Technology.


There will be time for coffee and mingle after the presentation. Please register so that we can estimate the number of participants.


Abstract
In many areas, such as image recognition, natural language processing, search, recommendation, autonomous cars, systems software and infrastructure, and even Software Engineering tools themselves, Software 2.0 (= programming using learned models) is quickly swallowing Software 1.0 (= programming using handcrafted algorithms).

One way to try to prepare for this ML-induced disruption is to focus on what is not changing.  Neural nets are pure functions from tensors to tensors that are differentiable, which allows them to be trained using back propagation. Software 2.0 Engineers construct complex neural nets like CNNs, RNNs, LSTMs, … using high-order combinators like map, fold, zip, scan, recursion, .... The programming language community has discovered a deep connection between back-propagation and continuations. This has led to the idea considering Differentiable Programming as the natural next step of Deep Learning.

This talk will illustrate the deep programming language principles behind Differentiable Programming, which will hopefully inspire the working Software 1.0 engineer to pay serious attention to the threats and opportunities of Software 2.0.

Biography
Erik Meijer received his Ph.D. from Nijmegen University in 1992. He was an associate professor at Utrecht University. He then became a software architect for Microsoft where he headed the Cloud Programmability Team from 2000 to 2013. He then founded Applied Duality Inc. In 2011 Erik Meijer was appointed part-time professor of Cloud Programming within the Software Engineering Research Group at Delft University of Technology. He is also member of the ACM Queue Editorial Board. In October 2015 Erik Meijer joined the Developer Infra Structure organization at Facebook where he works on leveraging ML to make developers more productive.

Meijer’s research has included the areas of functional programming, particularly Haskell, parsing, programming language design, XML, and foreign function interfaces. His work at Microsoft included C#, Visual Basic, LINQ, Volta, and the reactive programming framework (Reactive Extensions) for .NET. In 2009, he was the recipient of the Microsoft Outstanding Technical Leadership Award and in 2007 the Outstanding Technical Achievement Award as a member of the C# team.




Category Seminar
Location: Palmstedtsalen, university building,
Starts: 12 November, 2018, 13:00
Ends: 12 November, 2018, 15:00

Published: Thu 11 Oct 2018. Modified: Fri 12 Oct 2018