/stanford_cs231n_2019

Solutions and comments to assignments for 2019 Stanford's course on convolutional neural networks

Primary LanguageJupyter Notebook

Assignment 1

Assignment 2

Assignment 3

Passing cs231n together within the OpenDataScience community

Next start - from 02.12.2019 till 08.03.2020

Main links

  • The course itself
  • Video-lectures, youtube channel. Prerequisites are given in the 1st lecture
  • Syllabus with assignments

Assignments

There are 3 big and tough assignments in this course. We’ll have deadlines and exemplar solutions (by me or smb else) to be discussed.

Competitions & projects

In the original course they've got projects. You can also complete one, but actually, lectures and assignments is already a good workload. To do smth more, I propose 3 variants:

  • a personal pet-project (will be nice to show in your portfolio) here is an example by @artgor and a description in 🇷🇺 (you can translate it, but the app is self-explanatory)
  • a Kaggle competition. Maybe a playground one, to start with. This one, persay: "Dog Breed Identification"
  • you can also write a tutorial

GPUs

Authors claim that you can pass the course even with typical hardware. However, I recommend to rent a machine with GPU. The most convenient option right now is either Google Colaboratory (tutorial on Medium) or even Kaggle Kernels (just switch on GPU in Kernel settings).

Plan