Yann LeCun, the director of AI research at Facebook, recently argued that ‘Deep Learning’ has out-lived its usefulness. As such, he proposed that it’s time for a new buzzword to reflect the development of a new kind of software - Differentiable Programming.
In this episode of LokadTV, we continue our mini-series by looking at Differentiable Programming’s origins and understanding where this technology actually emerged from. We discuss how the thinking behind it varies from the neural networks of old and why we are revisiting theories such as stochastic gradient descents and automatic differentiation, which have already been around for well over 50 years.
For Differentiable Programming to come about, there were a number of basic intuitions that needed to be proved completely wrong, but its development has been incredibly incremental. We understand why the classic idea of mimicking biological processes through technology leads to inefficiencies and discuss how software can have an affinity with its underlying hardware. We learn how to combine the different statistical models that are currently being used through floating points. Finally, we discuss how Differential Programming provides the ability to capture highly complex patterns and the capability of an open toolkit for optimization.
Yet, how exactly can new technological advances such as image and sound recognition, incredible though they may be, possibly be linked to supply chain optimization? Watch the video and find out.
00:29 Differentiable Programming: did we really need another buzzword?
06:28 It was quite an iterative approach to get to Differentiable programming. Is that right?
09:40 What was the inspiration behind Differentiable Programming?
12:30 How do you implement the code behind Differentiable Programming?
15:25 How can you know that you are going to have the right answer if there are those blank spaces?
16:22 How closely is the R&D we are doing here at Lokad linked to the work in Differentiable Programming they are doing at the Facebooks of the world?
18:19 How can AI problems, like image recognition, be related to supply chain?
20:15 What is the key benefit of Differentiable Programming to Lokad? Is it the idea of answering all those unknowns that are out there in the Supply Chain world?
22:17 What are the big challenges that Differentiable Programming introduces?