Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Algorithms, AI & Machine Learning
1: Introduction & Overview
Welcome to the course! (13:12)
The state of algorithmic risk (8:36)
Demarcating the sociotechnical system (8:59)
Course Resources
2: Conceptual Overview
General taxonomy (14:28)
Methods (22:03)
Model - Inference - Learning paradigm (8:13)
Intelligent Agents (17:34)
Written Exercise #1
3: Classic Algorithms
Data Structures (26:21)
Basic Statements (15:46)
Functions (10:17)
4: Handcrafted Knowledge & Artificial Intelligence
Knowledge representation (16:57)
Feature selection & engineering (14:22)
Practice Exercise 1: Putting your knowledge to work
5: Classification Problems
K nearest neighbors (12:07)
Decision trees (15:00)
Support vector machines (7:22)
6: Linear Networks
Overview (2:26)
Modeling (4:35)
Inference (12:11)
Learning (14:47)
Gradient Descent (17:07)
Practice Exercise 2: Training your own model
7: Deep Neural Networks
Multi-layer neural networks (15:14)
Backpropagation (10:55)
Convolutional neural networks (19:24)
Recurrent networks (19:36)
8: Reinforcement Learning
Background: {states, actions, rewards, values, policies} (21:34)
Model-based methods (19:11)
Model-free methods (11:17)
Deep RL (17:23)
9: Natural Language Processing
Bias in NLP Lecture
Synthetic media, GANs, Deepfakes (21:16)
Large Language Models (28:34)
10: Computer Vision
Object detection (16:27)
Facial recognition (14:45)
11: Miscellaneous
Bias testing
Final Practice Exercise (4:41)
Gradient Descent
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock