Self-Driving Car Engineer Diary — 1

Hi. This is the 1st in a series of short posts where I will capture what I found most interesting during my education journey to become a qualified Self-Driving Car Engineer. Hope you enjoy the ride as much as me!

Thu, 8/Dec/2016

Pre-course preparation

1. Joined Udacity’s open-source self-driving car build challenges : formed open, global, collaborative team ‘ai-world-car’ with goal of donating any prize money to charity (UNICEF). ~= 300 members with ~= 10 active contributors. We placed 8th in Challenge 2, round 1. Great way to learn and swap ideas with fellow students, get to know the Udacity staff (who really put their students interests first)+ larger global community.
2. Upgraded development environment for deep learning : Alienware Aurora with GTX1080 GPU + Acer Chromebook 14 for remote access to ‘my rig’. Increased data limit to home (for those 10’s of GB video training data-sets for deep learning) and phone (for remote access and learning on the go). You know your committed to something when you happily spend most of your savings on education fees / resources and environment!
3. Maths time : I REALLY want a deep understanding of the material so followed Gilad Gressel’s recommendation (course mentor): Essence Of Linear Algebra (for linear classifiers which is step 1 towards CNNs), Gradients & Derivatives (for back propagation understanding) and CS231n: Convolutional Neural Networks for Visual Recognition lectures (for full Neural Networks and Convolutional Deep Neural Networks understanding).

Bring on next week!