Download as PPTX, PDF, TXT or read online from Scribd
Download as pptx, pdf, or txt
You are on page 1/ 34
Electrical Machine Drives
Dr. Arsalan Arif
AI for Mechanical Engineering
Introduction
Spring Semester 2024
Definition of Machine Learning Arthur Samuel (1959): Machine Learning is the field of study that gives the computer the ability to learn.
[Kevin Murphy] algorithms that
• automatically detect patterns in data • use the uncovered patterns to predict future data or other outcomes of interest Definition of Machine Learning
Experience (data): games played by the
program (with itself) Performance measure: winning rate Definiti ons ▪ Artificial Intelligence ▪ Machine Learning ▪ Deep Learning Deep Learning Example Classic Machine Machine Learning Feature Classifi er Learning Detection “Ali" Step 1: features. Algorithm Determine Step 2: Feed them We through model. choose Deep Learning Neural Network Steps 1 and 2 are “Ali" combined into 1 step.
5 Two Main Types of Machine Learning Dataset Goal Example
Supervised Make Fraud
Has a target column Learning predictions detecti on
Unsupervised Does not have a Find structure Customer
Learning target column in the data segmentati on
6 Supervised Learning If the shape of the object is rounded and has a depression at the top, is red in color, then it will be labeled as –Apple. If the shape of the object is a long curving cylinder having Green-Yellow color, then it will be labeled as –Banana
Now suppose after training the data, you have given a new separate fruit, say Banana from the basket, and asked to identify it.
Since the machine has already learned the things from previous data It will first classify the fruit with its shape and color and would confirm the fruit name as BANANA and put it in the Banana category. Thus the machine learns the things from training data(basket containing fruits) and then applies the knowledge to test data(new fruit).
Supervised Learning is classified into
•Classification: A classification problem is when the output variable is a category, such as “Red” or “blue” , “disease” or “no disease”. •Regression: A regression problem is when the output variable is a real value, such as “dollars” or “weight”. Unsupervised Learning
Suppose it is given an image having both dogs and cats which it has never seen.
Thus the machine has no idea about the features of dogs and cats so we can’t categorize it as ‘dogs and cats ‘
It can categorize them according to their similarities, patterns, and differences
We can easily categorize the above picture into two parts.
The first may contain all pics having dogs in them and the second part may contain all pics having cats in them.
Here you didn’t learn anything before, which means no training data or examples.
It allows the model to work on its own to discover patterns and information that was previously undetected. It mainly deals with un-labelled data. Taxonomy of Machine Learning (A Simplistic View Based on Tasks)
Supervised Unsupervised Learning Learning
Reinforcement Learning Taxonomy of Machine Learning (A Simplistic View Based on Tasks)
Supervised Unsupervised Learning Learning
Reinforcement Learning
Can also be merged
What is Machine Learning ? (by examples) Classification (from data to discrete classes) Classification+ localization = detection
Classification Regression (predicting a numeric value)
Output values real values or integers
Supervised Learning Housing Price Prediction Given: a dataset that contains samples
Learn a function f(x) to predict y given x
Task: if a residence has square feet, predict its price?
15th sample Housing Price Prediction Given: a dataset that contains samples
Task: if a residence has square feet, predict its price?
fitting linear/qaudratic functions to the dataset
More Features Suppose we also know the lot size Task: find a function that maps (size, lot size) price
features/input label/output 𝑦 Dataset: where “Supervision” refers to 𝑥2
𝑥1 High-dimensional Features for large E.g.,
[] --- living size 𝑥1 --- plot size --- # floors 𝑥2 --- condition --- price 𝑥3 𝑥= ⋮ ⋮ ⋮ 𝑥𝑑 Clustering “After unsupervised” discovering structure in data Regression vs Classification regression: if is a continuous variable e.g., price prediction classification: the label is a discrete variable e.g., the task of predicting the types of residence
(size, lot size) house or townhouse?
house or townhouse? Supervised Learning in Computer Vision Object localization and detection raw pixels of the image, the bounding boxes
ImageNet Large Scale Visual Recognition Challenge. Russakovsky et al.’2015
Supervised Learning in Natural Language Processing Machine translation Unsupervised Learning Unsupervised Learning Dataset contains no labels: Goal (vaguely-posed): to find interesting structures in the data supervised unsupervised Clustering Un Supervised Clustering Words with Similar Meanings (Hierarchically)
[Arora-Ge-Liang-M.-Risteski, TACL’17,18] Reinforcement Learning Reinforcement Learning The algorithm can collect data interactively
Try the strategy and Data Improve the strategy
collect feedbacks collection Training based on the feedbacks Various Algorithms
