Artificial Intelligence and Machine Learning notes
43 notes by 37 users · Page 1 of 2
This page gathers over 30 user-made notes on Artificial Intelligence and Machine Learning, from expert systems to language processing and computer vision. The collection is mostly university-level, with material for professional candidates and school students, as well as teachers seeking teaching material. Use it to review learning methods and explore AI topics. Choose a note to start reading.
Select topic
Notes
-
Expert Systems Created via:1. Knowledge acquisition via domain expert, knowledge engineer and domain user. Can be difficult - vague answers, intuition, lack of support for change by expert.2. Knowledge representation (Prolog, IF &nb...
-
8 Applications of Computer Vision in Artificial Intelligence (AI) Computer vision and human vision are similar, but humans have the advantage of experience, which is a considerable advantage. Humans acquire contextual information throughout their lives, which aids with object recogn...
-
Natural Language Processing
-
AI SECOND QUESTIONS 2015 2 (i) Give a description and example of a Simple Agent with no internal states and how it works using only the surface appearance of the language. [4 marks] In a simple agent it has no internal state. The environ...
-
Google's Five key Problems for Robot Safety Google's AI researchers say these are the five key problems for robot safety The robots are perfectly safe; it's you Google's worried about Google is worried about artificial intelligence. No, not that it will become ...
-
Past Paper AI 2016
-
Week 6 when errors exist in ML algorithm ? - add more training data - add more features - remove features - try polynomial fit - try increasing lambda -Try decreasing lambda Use diagnostic: that tells how accurately t...
-
Machine learning paper explained LOOK AHEAD OPTIMIZER : K STEPS FORWARD 1 STEP BACKWARD https://www.youtube.com/watch?v=ypqf7UUird4 Stochastic weight optimizing : taking weight average when in weight space Regularized non linear acc...
-
Probabilistic parsing Statistical Parsing ==================================================================================== -- using statistical models for AMBIGUITY (PP-attachment), guiding parsing, most like...
-
Perceptrons and Sigmoid Two important types of artificial neuron (the perceptron and the sigmoid neuron) standard learning algorithm for neural networks, known as stochastic gradient descent Perceptrons A perceptron takes several binary inpu...
-
Untitled Goal: Develop a cost-effective and accurate vehicle speed estimation system using monocular video data. Why It's Important: This approach addresses the limitations of traditional hardware-based systems like LiDAR and ...
-
Untitled Goal: Develop a cost-effective and accurate vehicle speed estimation system using monocular video data. Why It's Important: This approach addresses the limitations of traditional hardware-based systems like LiDAR and ...
-
Introduction Notes Introduction Intro ML code is often the smallest part of an ML solution Most revolves around data (pipelines, validation, feature extraction, etc) MLOps = a set of processes and automation for managing code, data, and...
-
Intro What is machine learning? science of making computers learn without being explicitly programmed; Tom Mitchell; : learning from experience E , to perform a Task T, on performance measure P , so long as performanc...
-
OKR Arthur Samuel (1958) - Field of study that gives computers ability to learn without being explicitly programmed. Tom Mitchell (1998) - A computer program said to learn from Experience E on some task T whose performanc...
-
Autonomous Vehicles Nowadays, AI is quickly surrounding us and affecting our daily lives. Its being used in products and services that we use on a daily basis like predicting texts, voice recognition and image recognition. Self driving c...
-
week4
-
Learning by Building Identification Trees - created from Mind Map Identification Tree Disorder formula From Trees to rules
-
Transfer Learning What id transfer Learning? The knowledge from learning in one setting is reused to improve learning in another setting. Transfer learning is inspired by the way human learners take advantage of their existing knowledg...
-
eScience Neural NLP - created from Mind Map Tasks Architectures Data Representation
-
RNN Encoder-Decoder - created from Mind Map Encode a variable-length sequence into a fixed-length vector representation Decode a given fixed-length vector representation back into a variable-length sequence From a probabilistic perspective, this model is a gene...
-
Face Detection
-
Untitled
-
Intelligent Agents - creado desde un Mapa Mental Properties Some agent types Multiagent Systems
-
Google creates AI robots that can learn on their own Google's parent company Alphabet is getting back into robots, but this time it's using AI to create robots that can learn on their own Alphabet's X group, the R&D lab formerly known as Google X, introduced t...
-
kERAS Keras makes it easy to turn models into products Your Keras models can be easily deployed across a greater range of platforms than any other deep learning framework: On iOS, via Apple’s CoreML (Keras support...
-
ARTIFICIAL INTELLIGENCE - created from Mind Map USES GOALS CHALLENGES
-
Lesson 1 Older definition By Arthur Samuel : The field of study that gives ability to computer to learn without being explicitly programmed. Newer Definition by Tom Mitchell :- A Computer program is said to learn fr...
-
Gen AI Generative AI Automation, adapativity Gen ai creates new text or images through prompts AI in daily life - Websearch, credit card payment, Amazon What i'll learn - How gen ai works, gen ai proj...
-
Open CV - Next Steps http://www.pyimagesearch.com/2016/12/05/macos-install-opencv-3-and-python-3-5/Having completed the compilation and installation of Open CV on my Mac, this website gives some great next steps for exercises and learning...
-
Untitled Discriminative Parsing --- Reranking parserIncremental Parsing --- Roark's parserUnsupervised parsing --- CCM(EM), Dependency(EM), Alignment(Metropolis-Hastings)Unsupervised tagging --- HMM(EM), BHMM(Gibbs samplling)U...
-
ELIZA - created from Mind Map Formation Formation Functionality
-
Untitled Machine Learning Definitions: "The field of study that gives computers the ability to learn without being explicitly programmed." (Arthur Samuel) "A computer program is said to learn from experience E with respect to ...
-
week 5 cost function for neural networks: input layer : hidden layer : output unit L = total number of layers in network sl = no of units in layer l; binary classification : 0 or 1; Sl = 1 ; K =1 ; m...
-
Untitled MNIST Neural Network Datase NMIST Neural Network
-
test sample The Apache OpenNLP library is a machine learning based toolkit for the processing of natural language text. It supports the most common NLP tasks, such as tokenization, sentence segmentation, part-of-speech tagging, n...
-
Expert Sytems - created from Mind Map What are they? Computer-based Make use of human knowledge Solves problems with expert knowledge Made up of User Interface Inference Engine Knowledge Base Editor Knowledge Base Chaining Forward Chaining Backward Chaini...
-
MP neuron MODEL Model is the approximation function that we assume holds the relation between the training input and output An example is y = mx+c , where m is the parameter When specifying a model , we need t...
-
Untitled activation function- When the weighted sum of input is fed as input to the activation function, it decides which nodes should fire for feature extraction. types of activation function: a. sigmoid function ...
-
Agents An agent is something that acts in an environment. An agent can, for example, be a person, a robot, a dog, a worm, a lamp, a computer program that buys and sells, or a corporation. Agents receive information...
More Artificial Intelligence and Machine Learning resources
About artificial intelligence and machine learning notes
GoConqr OriginalArtificial intelligence and machine learning notes
These notes offer different ways into the unit. Expert Systems describes knowledge acquisition, while Perceptrons and Sigmoid introduces two types of artificial neuron. For language topics, the notes on neural natural language processing include tasks such as sentiment analysis and machine translation. Face Detection contains a code example using OpenCV.
How to revise with notes
Start with Intro if you want a definition of machine learning and a way to think about learning from experience. If you are working on neural networks, move to Perceptrons and Sigmoid and make a short summary of the two neuron types.
Read a note in sections, then write down the ideas you can recall without looking. Return to the note to check your summary. When you want to test recall in a different way, switch to a quiz or flashcards on the unit page. Pick a topic and explore the notes that match it.
Frequently asked questions
Which note should I start with?
Try Intro if you want to begin with a definition of machine learning and the idea of learning from experience. If your current topic is neural networks, Perceptrons and Sigmoid is another starting point. Choose the note that is closest to the work you are revising.
What topics do these notes cover?
The collection includes notes on expert systems, intelligent agents, neural networks, natural language processing and computer vision. Face Detection contains an OpenCV code example, while Probabilistic parsing discusses statistical models for ambiguity. You can browse the titles to find a topic that matches your current work.
Are the notes free to use?
Yes. Every note listed here is free to open and study without an account. The resources were made by GoConqr users, not by GoConqr. A free account also lets you save quiz scores and make your own quizzes, mind maps, flashcards and notes.