The Strange Loop in Deep Learning

Where he describes this self-referential mechanism as what describes the unique property of minds. The strange loop is a cyclic system that traverses several layers in a hierarchy. By moving through this cycle one finds oneself where one originally started. Coincidentally enough, this ‘strange loop’ is in fact is the fundamental reason for what Yann LeCun describes as “the coolest idea in machine learning in the last twenty years.” Loops are not typical in Deep Learning systems. These systems have conventionally been composed of acyclic graphs of computation layers. However, as we are all now beginning to discover, the employment of ‘feedback loops’ are creating one of the most mind-boggling new capabilities for automation. This is not hyperbole, this is happening today where researchers are training ‘narrow’ intelligence systems to create very capable specialist automation that surpass human capabilities.

What Are Artificial Intelligence, Machine Learning, and Deep Learning?

AI and Machine Learning have become mainstream, and people know shockingly little about it. Here is an explainer and useful references.

R 3.4.1 is released – with some Windows related bug-fixes

R 3.4.1 (codename “Single Candle”) was released several days ago.

Volatility modelling in R exercises (Part-3)

This is the third part of the series on volatility modelling. For other parts of the series follow the tag volatility. In this exercise set we will use GARCH models to forecast volatility.

Using simulation for power analysis: an example based on a stepped wedge study design

Simulation can be super helpful for estimating power or sample size requirements when the study design is complex. This approach has some advantages over an analytic one (i.e. one based on a formula), particularly the flexibility it affords in setting up the specific assumptions in the planned study, such as time trends, patterns of missingness, or effects of different levels of clustering. A downside is certainly the complexity of writing the code as well as the computation time, which can be a bit painful. My goal here is to show that at least writing the code need not be overwhelming. Recently, I was helping an investigator plan a stepped wedge cluster randomized trial to study the effects of modifying a physician support system on patient-level diabetes management. While analytic approaches for power calculations do exist in the context of this complex study design, it seemed worth the effort to be explicit about all of the assumptions. So in this case I opted to use simulation. The basic approach is outlined below.