01 : Intro to ML Flashcards
(12 cards)
1
Q
What is ML?
A
Programming computers to learn from observational data by identifying pattern and relationships.
These learned patterns are then used to analyze new data and make predictions or decisions.
2
Q
Why we use ML?
A
- Automation of Tasks
- Predective analysis
- Handling big data
- Improved accuacy
- Customization and Personalization
3
Q
When we should use ML?
A
- When The problem can’t be solved with simple rules
- When patterns need to be identified.
- For predictive insights
- To automate repetitive tasks
- For personalization
4
Q
Types of systems of ML?
A
- Supervised
- Unsupervised
- Semi-Supervised
- Reinforcement Learning
5
Q
Supervised learning ?
A
Trained on labeled dataset, where each input data point is paired with a corresponding output.
6
Q
Supervised learning algorithms ?
A
- K-nearest neighbors
- Linear regression
- Neural networks
- Support vector machines
- Logistic regression
- Decision trees and random forests
7
Q
Unsupervised learning ?
A
- Trained with unlabeled data and must identify underlying patterns or structures in the data.
8
Q
Unsupervised learning algorithms ?
A
- Clustering : K-means, hierarchical cluster analysis
- Association rule learning : Eclat, Apriori
- Visualization and dimensionality reduction : kernal PCA, t-distributed, PCA
9
Q
Semi-supervised learning ?
A
- A mix of both supervised and unsupervised approaches, where the dataset has a small amount of labled data and a large amount of unlabled data.
10
Q
Reinforcement lerning ?
A
Learns through intereractions with an environment, receiving feedback in the form of rewards or penalties.
11
Q
Examples of supervised machine learning tasks ?
A
- Identifying the zip code from handwritten digits on an envelope.
- Determining whether a tumor is begin based on a medical image.
- Detecting fraudulent activity in credit card transactions
12
Q
Examples of unsupervised machine learning tasks ?
A
- Identifying topics in a set of blog posts
- Segmenting customers into group with similar preferences
- Detecting abnormal access patterns to a websites
