Due Date: TBD Need help? Remember to check out Edstem and our website for TA assistance. Downloads Like in some previous homeworks, this assignment will take place in a Python notebook file. Please click here to download the assignment code. Handin Your handin should contain:

Due Date: 4/8 @ 11:59 PM Need help? Remember to check out Edstem and our website for TA assistance. Downloads Like in some previous homeworks, this assignment will take place in a Python notebook file. Please click here to download the assignment code. Handin Your handin should contain:

Due Date: 4/8/2025 Need help? Remember to check out Edstem and our website for TA assistance. :::danger Please make sure to run the following command in your environment before starting the assignment: pip install gymnasium==1.1.1 :::

Due Date: 3/18/2025 Need help? Remember to check out Edstem and our website for TA assistance. Assignment Overview Welcome to Homework 7! You'll start this assignment by building a logistic regression model, then learn how to calculate gradients automatically and explore neural networks using the PyTorch library, gaining hands-on experience with the deep learning pipeline. Here's what you'll learn and explore: Fundamentals of logistic regression Backpropagation with PyTorch Building basic neural networks with PyTorch

Due Date: Tuesday, 3/11 at 11:59pm Need help? Remember to check out Edstem and our website for TA assistance. Assignment Overview The topic of this assignment is linear regression, a means of computing a set of coefficients $w \in \mathbb{R}^{d}$ given a matrix $X \in \mathbb{R}^{n \times d}$ such that $X w \in \mathbb{R}^{n}$ approximates a vector $y \in \mathbb{R}^{n}$. You will run a simple linear regression on just one variable (i.e., $d = 1$), and you will run a polynomial regression, where you transform the columns of $X_k$ to alternatives like $X_k^2$ and $X_k^3$. Using all of this machinery, you will build a model from a real-world data set to estimate life expectancy, given explanatory variables like health outcomes, population size, education level, and so on. First, you will compare simple linear regression, a model with high bias and low variance, to multiple linear regression, a model with low bias and high variance. Then you will perform an analysis of the bias-variance trade-off on synthetic data. Finally, you will return to the modeling task, where you will use regularization to select a model with a good balance of bias and variance. Learning Objectives

<span style="font-size:2em;"><b>Foundations of AI</b></span> <span style="font-size:1.25em;"> Eric Ewing</span> Time: M/W/F 1:00-1:50pm, Location: MacMillan 117 Instructor Office Hours: Wednesdays 3-5pm Tuesdays 3-5pm Location: Arnold Lab 305

Due Date: TBD Need help? Remember to check out Edstem and our website for TA assistance. Downloads Like in some previous homeworks, this assignment will take place in a Python notebook file. Please click here to download the assignment code. Handin Your handin should contain:

Due Date: TBD Need help? Remember to check out Edstem and our website for TA assistance. Assignment Overview Welcome to Homework 7! You'll start this assignment by building a logistic regression model, then learn how to calculate gradients automatically and explore neural networks using the PyTorch library, gaining hands-on experience with the deep learning pipeline. Here's what you'll learn and explore: Fundamentals of logistic regression Backpropagation with PyTorch Building basic neural networks with PyTorch

Due Date: Friday, 2/28 at 11:59pm Need help? Feel free post on Edstem for TA assistance. Assignment Overview Constrained optimization is one of the most widely applicable topics that we cover in this class. It has been around a lot longer than deep learning, and even with all the hype around the latter, it remains a fundamental tool driving every part of the world economy. From planning air travel schedules to determining the NFL schedule, mathematical programs are used everywhere. In this homework, you will model and solve two specific problems that require constrained optimization: 1) risk management in investing and 2) planning a clean energy grid for the state of Rhode Island. You will do so using the python library CVXPY. In Part 1 of this homework, you will be tasked with choosing a portfolio of stocks to invest in. You will construct your portfolio to maximize expected returns while ensuring your risk remains below some acceptable threshold. In Task 1, you will derive an expression for risk. In Task 2, you will program a model that uses real historical stock data to make purchasing decisions.

Due Date: Tuesday, 3/4/2025 at 11:59pm Need help? Remember to check out Edstem and our website for TA assistance. Python Notebooks A Python notebook is an application that allows users to combine text, code, and visualizations, much like a traditional scientific lab notebook. This assignment is written in a Python notebook. In the file, we describe the tasks, and ask you to insert the code and run it to generate the requisite visualizations. Your handin should include the Python notebook file--modified--as well as your README, as always.

Overview The course uses Python as our language. As software library installation and management can often be tricky, Python supports virtual environments which collect and isolate a set of packages and their versions. CSCI 410 has its own virtual environment to reduce configuration issues. Assignment 0 tasks you with setting up this environment locally. Software and Tools Python Version: Python 3.10.6. As our autograder exclusively runs 3.10.6, we will not provide support for other versions of Python. Editor: Visual Studio Code (VSCode), a free cross-platform editor with debugging support. Virtual Environment Setup on a Personal Machine Preparation Download VSCode if you haven't already.

Due Date: 2/21 at 11:59pm Need help? Feel free post on Edstem for TA assistance. Assignment Overview The most famous problem in computer science is Satisfiability (a.k.a. SAT). This problem asks whether there exists a satisfying assignment for a Boolean formula, i.e., a formula of propositional logic. It was made famous by Stephen Cook in 1971, when he established it as the first NP-complete problem. A problem is in the class of NP problems if it can be solved in nondeterministic polynomial time, which means that an answer can be guessed and checked in polynomial time. (The guessing is what motivates nondeterministism in the name.) Not only is SAT in this class, it is "complete" for this class, which means that every problem in this class can be reduced to SAT in polynomial time. And what this means is that if we have a SAT solver, we can use it to solve any NP-complete problem. Your task in this assignment is to build a SAT solver! Arguably the most important question in all of computer science is whether P = NP. That is, are problems in the class NP solvable in polynomial time? Common wisdom suggests that the answer to this conundrum is no, they are not. But as of yet, there is no proof of this claim one way or the other.

<span style="font-size:2em;"><b>Foundations of AI</b></span> <span style="font-size:1.25em;">Professors Amy Greenwald and Eric Ewing</span> MWF 1-1:50pm, List 120 Course Content This course will provide broad coverage of core topics in artificial intelligence (AI), as a prelude to students taking more in-depth AI courses later on. To this end, the course will introduce students to prevalent AI models, both logical and probabilistic, as well as algorithms to solve these models based on search, planning, reinforcement learning, and supervised and unsupervised machine learning. These ideas will be applied to develop basic natural language processing, computer vision, robotic, and multiagent systems, all with an eye towards building socially responsible AI. Note: CS 410 and CS 1411 share the same course staff, lectures, discussions, and assignments. Enrollment in CS 410 is limited to students with a semester level of 03 or 04. Upper-level undergraduate and graduate students should enroll in CS 1411, for which final project expectations will be higher. Neither course can be capstoned. Academic Learning Objectives

Due Date: 2/11/2025 at 11:59pm Need help? Feel free post on Edstem for TA assistance. Assignment Overview Humans have dreamed of a chess-playing machine since at least 1770, with the advent of Mechanical Turk. More recently, Alan Turing, the father of computer science, designed a chess-playing program with two steps of lookahead. His work was built upon by Claude Shannon's groundbreaking 1950 paper, in which he outlined the minimax algorithm. All of the aforementioned work was theoretical, as machines were not yet capable of playing games. By 1959, however, Arthur Samuels had designed and built a checkers-playing machine. Samuels algorithm employed $\alpha\beta$-pruning. Moreover, his machine learned by playing games against itself--and the term machine learning was coined! Today's game-playing programs, which also learn in self-play, have surpassed human performance in substantially harder games, including Backgammon, Chess, Poker, and Go. All of these games are adversarial: they are played by two players, with one winning and the other losing (unless there is a draw).

Due Date: 2/4/2025 at 11:59pm Need help? Feel free post on Edstem for TA assistance. Assignment Overview Last assignment was concerned with blind search. Although blind search will eventually find an optimal solution to a search problem, it may take more time (e.g., seconds) than the number of atoms in the universe. This assignment is designed to introduce you to heuristic search. Heuristic search is not always guaranteed to find an optimal solution, but heuristics are useful nevertheless because they can speed up search and/or they can save on memory requirements. In this assignment, you will experiment with BFS, DFS, and an additional blind search algorithm, iterative deepening, on small instances of a simple Tile Game to evaluate their run times and memory usages. Additionally, you will implement A* search, a heuristic search algorithm, which you will seed with two different heuristics, in order to compare their performance on larger instances of the Tile Game.

==Due Date: 2/4/2025 at 11:59pm== Need help? Feel free post on ==Edstem== for TA assistance. Assignment Overview Welcome to CS410! In this assignment, you will prepare your local development environment, and then use it to complete your first programming task. In the first part of this assignment, you will install and setup the software you will be using throughout the course, and you will familiarize yourselves with the platforms you will be using to download, develop, and submit assignments. In the second part of this assignment, you will use your newly set up development environment to solve mazes using breadth-first and depth-first search.

Due Date: 10/23/2024 at 12pm Need help? Remember to check out Edstem and our website for TA assistance. Assignment Overview The topic of this assignment is linear regression, a means of computing a set of coefficients $w \in \mathbb{R}^{d}$ given a matrix $X \in \mathbb{R}^{n \times d}$ such that $X w \in \mathbb{R}^{n}$ approximates a vector $y \in \mathbb{R}^{n}$. You will run a simple linear regression on just one variable (i.e., $d = 1$), and you will run a polynomial regression, where you transform the columns of $X_k$ to alternatives like $X_k^2$ and $X_k^3$. Using all of this machinery, you will build a model from a real-world data set to estimate life expectancy, given explanatory variables like health outcomes, population size, education level, and so on. First, you will compare simple linear regression, a model with high bias and low variance, to multiple linear regression, a model with low bias and high variance. Then you will perform an analysis of the bias-variance trade-off on synthetic data. Finally, you will return to the modeling task, where you will use regularization to select a model with a good balance of bias and variance. Learning Objectives

Due Date: 10/9/2024 at 12pm Need help? Remember to check out Edstem and our website for TA assistance. Python Notebooks A Python notebook is an application that allows users to combine text, code, and visualizations, much like a traditional scientific lab notebook. This assignment is written in a Python notebook. In the file, we describe the tasks, and ask you to insert the code and run it to generate the requisite visualizations. Your handin should include the Python notebook file--modified--as well as your README, as always.