The previous documentation for Qbot is rendered irrelevant since most of the suggested Azure services were already discontinued or are going to be discontinued in a few years time. Overview The aim of this bot is to automate question answering in class Microsoft Team channels. In parallel to that, this bot will also build a knowledge repository of questions and answers, as well as provide a better visibility on the types of questions asked by students in different classes & over the years. Steps to Create Creating a Language Service & Knowledge Base A knowledge base is the repository of questions and answers that the language service can refer to when it looks up for questions. This resource can be created through this portal. When creating a KB, Azure will prompt you to create a question answering service in the Language Studio.

50.021 Artificial Intelligence Class Links eDimension Course Material Links Neural Networks and Deep Learning Deep Learning Book Assessments

{%hackmd theme-dark %} Section Title

Source {%hackmd theme-dark %} Basics Neural Networks is used when we can't draw a linear line to separate two classes. Some problems like XOR are unable to be separated using LinReg problems. It requires a more complex, polynomial problems. A deep neural network is a neural network with more than 1 layer (excluding the input/output layers).

{%hackmd theme-dark %} Overview Machine Learning What is it? Evaluating models Binary cross entropy Logistic regression

Motivating Questions Why do we behave differently in different groups? Why are relationships important? Social Needs :busts_in_silhouette: 2 theories of humans' social needs: Key Constructs of Group Dynamics Social Facilitation (Mere Presence Effect)

{%hackmd theme-dark %} Resource Limits Suppose we have 100 seconds, and we can explore 10^4^ nodes/second We can search 10^6^ nodes per move Standard Approach:

{%hackmd theme-dark %} Commutativity In CSPs, variable assignments are commutative. It doesn't matter which order you assign the variables e.g. [WA=red then NT=green] == [NT=green then WA=red] Only need to consider assignments to a single variable at each level/depth

{%hackmd theme-dark %} Outline & Objective Understand the differences between standard search problems and adversarial search problems Understand the workings behind the Minimax algorithm and α - β pruning Able to use Minimax algorithm to solve an adversarial/game search problem Able to use α-β pruning to speed up adversarial/game search Introduction

50.033 Foundations of Game Design and Development {%hackmd theme-dark %} Class Links Course Handout eDimension Class Recordings Assessments

{%hackmd theme-dark %} Outline & Objective Understand the differences between standard search problems and constraint satisfaction problems Able to formulate a constraint satisfaction problem Understand the workings behind backtracking search and the various heuristics (not the heuristics mentioned in the previous chapter) used to enhance its efficiency Able to use backtracking search to solve a CSP Standard Search Problem vs CSP

{%hackmd theme-dark %} Outline & Objective Understand the role that heuristic plays in informed search Understand the important properties of heuristics Admissible, consistent, dominance Able to design heuristics that are appropriate for specific problem instances, based on these properties:

Source: Lecture Video {%hackmd theme-dark %} Outline & Objectives Learn about two different informed search algorithms Greedy Best-First Search A* Search

Source: Lecture Video {%hackmd theme-dark %} Outline 5 different uninformed search algorithms Breadth-First Search Uniform cost search Depth-First Search

Source: Lecture Video {%hackmd theme-dark %} Outline & Objectives 5 different uninformed search algorithms Breadth-First Search Uniform-cost Search

Video Link Outline Formulate a problem in terms of state space, initial state, goal test, actions, transition model, path cost Understand the general characteristics behind search strategies Problem Solving Agents Motivating Example: Romania Holiday Formulate Goal:

Video Link Outline Basic idea behind rational agents and the agent model (PEAS description): Performance measure Environment Actuators Sensors

Video Link What is AI Definition: The study of how to produce machines that have some of the qualities that the human mind has, such as the ability to understand language, recognise pictures, solve problems, and learn. The advent of AI is brought about by the Turing Test, which was invented in 1950. The objective of this test is to determine whether the entity that the tester is conversing with is a human / machine. First Chatbot: "ELIZA". Very limited set of responses (feels like a state machine). More loosely, AI is an umbrella term for:

50.041 Distributed Systems and Computing {%hackmd theme-dark %} Class Info Class Info Notes Go Lecture

{%hackmd theme-dark %} Tanenbaum: Chapters 6.1, 6.2, 6.3 Distributed Systems Distributed Middleware encompasses all services between OS/Hardware, and the applications. 3 metrics to assess a distributed systems protocol: