Hello there! My name is Jamie, and here’s my Data Science origin story (reserved for the day when Marvel decides to create some more movies).
A few months ago, I was sitting in acting class, delivering lines to my partner over Zoom, and something was simply not right. All of a sudden, I was reminded of my compounding college loans and my lack of income. After finishing a COVID-ified semester of musical theatre training at Viterbo University, I decided that I needed to change course.
When beginning to build your first neural network, the process seems akin to feeling around for a needle in a haystack, blindfolded. There are a million hyper-parameters — learning rate, number of layers, number of nodes, batch size, activation function — and it seems that finding the optimal parameter is a stab at the dark, at best.
Today, we’re going to hopefully shed some light on this “black box” with the help of Sergey Ioffe and Christian Szegedy’s paper, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, to take a closer look at at least one of…
PyTorch has become one of the leading Machine Learning frameworks in the past couple of years, with various companies adopting its easy-to-use framework for their research. According to The Gradient, PyTorch is becoming a major competitor to the long-time favorite, TensorFlow, showing major growth in its mentions at research conferences.
The code below show’s PyTorch’s clever integration with idiomatic Python.
Just a few days ago, I had just finished reading through the instructions for a big modeling project that would be due the following week. After 5 weeks of more or less inhaling all there is to know about data science basics, my mind was a bit jumbled. I didn’t know how to sort through all the information.
Do you remember in that Intro to Psychology class you took in high school or college, when they talk about how the brain organizes information into “schemas”? …
Performed to my heart’s content for a year at music theater school (thank you Viterbo University) — dropped out and am now making lots of graphs.