Neural Decoding of Smell with Generative AI Masters of Science in Data Science Thesis Proposal
School of Professional Studies, Northwestern University
Abstract
Olfaction (sense of smell) and related structural abnormalities in the olfactory bulbs are among the first observed symptoms corelated with Alzhiemer’s disease (Esiri and Wilcock 1984; Thomann et al. 2009). The functional relationship between olfaction and the olfactory bulbs is poorly understood (Weiss et al. 2020). In the area of visual decoding, advances in machine learning using generative adversarial networks (GANs) have provided an unprecedented insight into neural decoding or the mapping of an individual brain’s responses and performance (Seeliger et al.
Image credit: R logo, Gopher Evaluating Go Unlike Python/R, Go is a compiled language that is more verbose but is said to run faster. For example, Uber, Amex and KhanAcademy find benefits with Go.
To benchmark Go’s performance and runtime against Python and/or R, here are various cases:
Performing least squares regression of the Anscombe Quartet (1973) Computing summary statistics of the California Housing Prices (Miller 2015) Web crawling and scraping of Wikipedia Identifying anomalies in the MNIST dataset Least squares regression with Python and R The Go implementation is benchmarked for runtime with a previous implementation by Miller (2015) in Python/R as a reference.
Partial image credit Why Go? Static site generators such as Hugo were developed recently using Go. Go is a compiled language designed for today’s multi-processor, scalable, high-performance systems. Other platforms have inherited dependency chains that can lead to infeasible build times. Realizing these benefits, Cloudfare recently migrated from Gatsby (a web framework based on JavaScript).
Demo website I first created a demo website using the Hugo Winston theme. This theme does have a Live Demo which made it simple to deploy onto Netlify.