Scribd
Upload
10 views3 pages

Ai

Uploaded by

barikanubhab5
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views3 pages

Ai

Uploaded by

barikanubhab5
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

1. what is ar ficial intelligence?

2. what is machine learning?


3. diff between machine learning and deep learning?
4. how related machine learning ai and deep learning?
5. some example of machine learning applica on?
6. types of ML?
7. diff between unsupervised and supervised ML?
8. diff between regression and classifica on?
9. exp different types of clustering?
10. what is pca ?
11. what is neural network?
12. what is McCulloch-pi s Nuron model with diagram?
13. what is back propaga on neural network?
14. what is transformer in machine learning?
15. what is ensamble learning?

Here's a comprehensive answer to all your ques ons:

1. What is Ar ficial Intelligence (AI)?

AI refers to the simula on of human intelligence in machines that are programmed to think, reason, learn, and
make decisions. AI enables systems to perform tasks such as problem-solving, speech recogni on, and decision-
making.

2. What is Machine Learning (ML)?

ML is a subset of AI that involves training algorithms on data so that they can learn pa erns and make
predic ons or decisions without being explicitly programmed. It focuses on crea ng models that improve with
experience.

3. Difference Between Machine Learning and Deep Learning

Machine Learning Deep Learning

Requires structured data. Works with large volumes of unstructured data.

Relies on feature extrac on. Automa cally performs feature extrac on.

Uses algorithms like SVM, decision trees. Uses neural networks with many layers.

Faster to train on smaller data. Requires significant computa onal power.

4. How Are Machine Learning, AI, and Deep Learning Related?

 AI is the broader field.

 ML is a subset of AI focused on learning from data.

 Deep Learning is a subset of ML that uses neural networks for high-complexity tasks.

5. Examples of Machine Learning Applica ons


 Email spam filtering

 Recommenda on systems (Ne lix, Amazon)

 Autonomous vehicles

 Fraud detec on

 Medical diagnos cs

6. Types of Machine Learning

1. Supervised Learning: Labeled data provided.

2. Unsupervised Learning: No labels; finds pa erns in data.

3. Reinforcement Learning: Learns through trial and error by receiving rewards or penal es.

7. Difference Between Unsupervised and Supervised ML

Supervised ML Unsupervised ML

Uses labeled data. Uses unlabeled data.

Aims to predict outcomes. Aims to find hidden pa erns.

Examples: Regression, classifica on. Examples: Clustering, dimensionality reduc on.

8. Difference Between Regression and Classifica on

Regression Classifica on

Predicts con nuous values. Predicts discrete labels.

Example: Predic ng house prices. Example: Spam or not spam.

9. Different Types of Clustering

1. K-Means Clustering: Divides data into k groups based on centroids.

2. Hierarchical Clustering: Builds a tree of clusters.

3. DBSCAN: Groups based on density.

4. Gaussian Mixture Model (GMM): Assumes data comes from Gaussian distribu ons.

10. What is PCA?

Principal Component Analysis (PCA) is a dimensionality reduc on technique that transforms data into principal
components to reduce complexity while retaining important informa on.

11. What is a Neural Network?


A neural network is a computa onal model inspired by the human brain. It consists of layers of interconnected
nodes (neurons) that process input data and generate outputs.

12. McCulloch-Pi s Neuron Model with Diagram

The McCulloch-Pi s model is a simple neural model that represents neurons as binary threshold units.

 Input: Weighted sum of inputs.

 Output: Binary (0 or 1) based on a threshold.


Diagram: A circle (neuron) receiving weighted lines (inputs), with an arrow showing the binary output.

13. What is Backpropaga on Neural Network?

Backpropaga on is a training algorithm for neural networks. It calculates the gradient of the loss func on and
updates the weights to minimize the error.

14. What is Transformer in Machine Learning?

Transformers are models designed for sequence-to-sequence tasks like natural language processing (NLP). They
use self-a en on mechanisms to process input sequences more efficiently than RNNs.

15. What is Ensemble Learning?

Ensemble learning combines mul ple models (e.g., decision trees, neural networks) to improve predic on
accuracy. Examples include bagging, boos ng, and stacking.

Let me know if you'd like further explana on on any topic!

You might also like