K-Nearest Neighbors

Cipher

JavaScript

Sentiment Analysis

Refugee Tweets

Cancer Diagnosis

Mental Health and ELIZA

Open Source Software

Algorithmic bias

Ethical Hacking

Web Security

CS + Climate Change

Cancer Detection with KNN

Trust and Safety

CS 106S Coding for Social Good Stanford University Winter 2023 This course applies fundamental CS concepts to social good problems, including health, government, education, and environment. Students will use their skills to create positive social impact. CS 106B is a recommended prerequisite. CS 106S is a survey course on the applications of fundamental computer science concepts from CS 106B to problems in the social good space (such as health, government, education, and environment). Each week consists of in-class activities designed by student groups, local tech companies, and nonprofits. Some of the topics we will cover include mental health chatbots, tumor classification with basic machine learning, sentiment analysis of tweets on refugees, and the ethical obligation of good security. Recommended prerequisite/corequisite: CS 106B. We're looking forward to a great quarter with you in CS106S! We know you are being equipped with the tools to make super cool stuff. However, sometimes it is difficult to see where these tools fit in the larger scheme of things. We want to show you ways to put the skills you have learned to good social use! Here are our objectives:

- Awareness: For students to gain awareness about the applicability of technology and computer science to enact social good in the world.
- Exposure: For students to learn how to utilize their skills to build tools and projects that create positive social impact.
- Utilization: For students to gain exposure to the variety of current projects and efforts to use computer science for social good.

Now, let's get into some important details: expectations, grading, and meeting time!  

CS 106S Coding for Social Good

Computer Programming

Linear Classifiers

Stochastic gradient descent (SGD)

Momentum

AdaGrad

Adam

Learning Rate Schedules

Support Vector Machine (SVM)

Softmax Loss

Multi-layer Perceptron

Backpropagation

Higher-level representations

Image Features

Pooling

Batch Normalization

Transfer learning

AlexNet, VGG, GoogLeNet, ResNet

Activation Functions

Data Processing

Weight initialization

Hyperparameter Tuning

Data Augmentation

Feature visualization and inversion

Adversarial Examples

DeepDream and Style Transfer

Single-stage detectors

Two-stage detectors

Semantic/Instance/Panoptic segmentation

Long Short-Term Memory (LSTM)

Gated recurrent unit (GRU)

Language Modeling

Image Captioning

Sequence-to-sequence (Seq2Seq)

Object Detection

Self-Attention

Transformer (machine learning model)

Video classification

3D CNNs

Two-stream networks

Multimodal Video Understanding

Supervised learning

Unsupervised learning

Pixel RNN, Pixel CNN

Variational autoencoder (VAE)

Generative adversarial network (GAN)

Pretext Tasks

Contrastive Learning

Multisensory Supervision

Optical Flow

Stereo Vision

3D Shape Representations

Shape Reconstruction

Neural Implicit Representations

Convolution

CS231n: Deep Learning for Computer Vision Stanford University Spring 2022 This is a deep-dive into the details of deep learning architectures for visual recognition tasks. The course provides students with the ability to implement, train their own neural networks and understand state-of-the-art computer vision research. It requires Python proficiency and familiarity with calculus, linear algebra, probability, and statistics. Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, localization and detection. Recent developments in neural network (aka “deep learning”) approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into the details of deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. During the 10-week course, students will learn to implement and train their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. Additionally, the final assignment will give them the opportunity to train and apply multi-million parameter networks on real-world vision problems of their choice. Through multiple hands-on assignments and the final course project, students will acquire the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks.  - Proficiency in Python  
    All class assignments will be in Python (and use numpy) (we provide a tutorial [here](http://cs231n.github.io/python-numpy-tutorial/) for those who aren't as familiar with Python). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Javascript) you will probably be fine.
- College Calculus, Linear Algebra (e.g. MATH 19 or 41, MATH 51)  
     You should be comfortable taking derivatives and understanding matrix vector operations and notation.
- Basic Probability and Statistics (e.g. CS 109 or other stats course)  
    You should know basics of probabilities, gaussian distributions, mean, standard deviation, etc. 

CS231n: Deep Learning for Computer Vision

Deep Learning

Computer Vision