My Top 3's

My top 3’s on a bunch of different topics. I hope future me isn’t too judgemental. Top Engineering Podcasts: Python Bytes Software Engineering Daily Changelog Network Top Linux Podcasts: Jupiter Broadcasting Network Ubuntu Podcast Late Night Linux Top Data Science Podcasts: Data Engineering Podcast Data Framed Linear Digressions Top Beers: Great Lakes Commodore Perry IPA Thirsty Dog 12 Dogs of Christmas Rhinegeist Brewery Truth IPA Top Cleveland East Side Parks:

Continue reading

TLDR; Data Engineering is the most important job title in your company that should have head count zero. Hint: just hire more Data Scientists. My thoughts on Data Engineering Please take everything said here as an opinion piece meant to be thought provoking. Definition: in this article “data engineer” is referring to the “ETL” consultant to the Data Science Team. If you’re a data engineer building data inrfastructure and reusable software components to empower the data science team, then please keep doing that.

Continue reading

JosiahNet: live coding a GOLANG Deep Learning Library SourceCode: github.com/thenomemac/josiahnet Inspired by Joel Grus’s youtube live coding of a deep learning frameworks, I wondered as a very new to GOLANG user could I live code a deep learning framework? It ended up taking a few hours to code this up as I didn’t have numpy as a starting point, but I found GOLANG to be very suitable for implementing a Deep Learning Library in Go with no dependencies.

Continue reading

TLDR; Train a neural net to identify midwestern fish specifes and create an interactive web app identify invasive specicies from user photos. whatismyfish.net is currectly in a mid-refactor state as I’m re-writing the python/flask web app in golang for fun and profit. Project Summary: The mobile web app WhatIsMyFish.net has been awarded 3rd place in the semi-final round of Eriehack.io : a first of its kind regional, eco focused engineering challenge.

Continue reading

This tutorial walks users through an entire deep learning based NLP pipeline. The notebook demos a sentiment model for IMDB movie reviews using an LSTM and benchmarks the model against a linear model with tokenized TFIDF features. The LSTM model is then introspected by looking at works most likely to flip a review from positive to negative and vice-versa. Then TSNE is used to visualize the the distribution of the most impactful words in movie reviews.

Continue reading

Author's picture

Josiah Olson

I’m interested in deep learning, deployment focused Data Sceince, and fly fishing.

Data Scientist Lead

Cleveland, OH