CS 540 Final Exam - Fast Learn Guide

Content locked

The catalog is public. Reading this content requires approved access.

Part 1: CNNs (Convolutional Neural Networks)

What It Is

1.1 Convolution Operation

1.2 Output Size Formula (MEMORIZE THIS)

1.3 Parameter Counting (MEMORIZE THIS)

1.4 Pooling

1.5 CNN Concepts (Memorize These)

Part 2: Deep Learning Concepts

2.1 Vanishing Gradient Problem

2.2 Residual Networks (ResNets)

2.3 Data Augmentation

2.4 Overfitting vs Underfitting

Part 3: Neural Network Basics

3.1 Perceptron

3.2 Activation Functions (MEMORIZE THESE)

3.3 Perceptron Calculation Example

3.4 XOR Problem

3.5 Cross-Entropy Loss

3.6 Gradient Descent

Part 4: Search Algorithms

4.1 Search Problem Setup

4.2 Uniform Cost Search (UCS)

4.3 A* Search (VERY IMPORTANT)

4.4 Admissible Heuristics (VERY IMPORTANT)

4.5 A* Search Example

4.6 Local Search: Hill Climbing

4.7 Simulated Annealing

Part 5: Game Theory

5.1 Normal Form Games

5.2 Dominant Strategy

5.3 Nash Equilibrium

5.4 Minimax Algorithm

5.5 Game Tree Size

Part 6: Reinforcement Learning

6.1 Markov Chains (The Core Idea)

6.2 Markov Decision Process (MDP)

6.3 Discount Factor γ

6.4 Value Iteration (VERY IMPORTANT - MEMORIZE THIS)

6.5 Value Iteration Example

6.6 Q-Learning

6.7 ε-Greedy Policy

Part 7: Linear Regression & Clustering

7.1 Linear Regression

7.2 K-Means Clustering

7.3 K-Means Example

Part 8: Quick Reference Formulas

CNNs

A* Search

Value Iteration

Q-Learning

Activations

Perceptron

K-Means

MSE

Part 9: Common Exam Tricks

CNN Tricks

Search Tricks

Game Theory Tricks

RL Tricks

Neural Network Tricks