Ai ML

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 4

1.

Differences between AI and ML

While artificial intelligence encompasses the idea of a machine that can mimic
human intelligence, machine learning does not. Machine learning aims to teach a
machine how to perform a specific task and provide accurate results by identifying
patterns.

2.Types of Machine Learning

There are several types of machine learning, each with special characteristics and
applications. Some of the main types of machine learning algorithms are as follows:

1. Supervised Machine Learning

2. Unsupervised Machine Learning

3. Semi-Supervised Machine Learning

4. Reinforcement Learning

3. Classification Algorithms may be used to solve classification problems such as Voice


Recognition, Identification of spam emails, Identification of cancer cells, etc.
Regression algorithms may be used to solve the regression problems such as House
price prediction, Weather Prediction, etc

4. Here are examples of machine learning at work in our daily life that provide value in many
ways—some large and some small.

 Facial recognition. ...


 Product recommendations. ...
 Email automation and spam filtering. ...
 Financial accuracy. ...
 Social media optimization. ...
 Healthcare advancement. ...
 Mobile voice to text and predictive text.
5. Advantages of Machine learning
1. Easily identifies trends and patterns
2. No human intervention needed (automation)
3. Continuous Improvement
4. Handling multi-dimensional and multi-variety data
Disadvantages of Machine Learning
1. Data Acquisition
2. Time and Resources
3. Interpretation of Results

6 .What does it mean to train an Artificial Neural Network ANN)

Each example needs to be made up of the input data and the desired output for that input. Training
an ANN is an iterative process in which training data examples are presented to the network one by
one, and the values of the weights are adjusted each time

7. Compare Biological Neural Network (BNN) with ANN

However, BNN neurons are more complex and diverse than ANNs. In BNNs, neurons have multiple dendrites
that receive input from multiple sources, and the axons transmit signals to other neurons, while in ANNs,
neurons are simplified and usually only have a single output.

8. What is the difference between perceptron and feed forward neural network?

The simplest type of feedforward neural network is the perceptron, a feedforward neural network
with no hidden units. Thus, a perceptron has only an input layer and an output layer. The output units
are computed directly from the sum of the product of their weights with the corresponding input units,
plus some bias.

9. What is an activation function and why use them?


The activation function decides whether a neuron should be activated or not by calculating the
weighted sum and further adding bias to it. The purpose of the activation function is to introduce non-
linearity into the output of a neuron.
10. Types of activation functions
Leaky ReLU

Softmax

Tanh

ReLU

Sigmoid

Rectified Linear Unit

Linear activation function

Binary step function

Sigmoid function

11. How Back Propagation model deviates from FFNM

During forward propagation, the input is fed into the neural network, and the network calculates the output.
During backward propagation, the error between the predicted output and the actual output is calculated,
and the weights and biases of each neuron are adjusted to reduce the error.

12. What is machine learning?

Machine learning is a subfield of artificial intelligence, which is broadly defined as the capability of a machine
to imitate intelligent human behavior.

13. What is ANN? Draw the basic model of an ANN

Most ANN algorithms have two common features. First, its network is composed of many artificial neurons
that are mutually connected. The connections are called parameters and learned knowledge from a data set
is then represented by these model parameters. This feature makes an ANN model similar to a human brain.

14. What is the learning rule?

A learning rule may accept existing conditions (weights and biases) of the network and will
compare the expected result and actual result of the network to give new and improved values
for weights and bias.

15. What do you mean by the terms “fuzzification” & “defuzzification”?

1. Fuzzification: This process involves converting crisp, precise input values into fuzzy values.
In traditional logic, inputs are typically either true or false, but in fuzzy logic, inputs can have
degrees of truth ranging between 0 and 1. Fuzzification allows for the representation of
uncertain or imprecise information in a structured way.
2. Defuzzification: Conversely, defuzzification is the process of converting fuzzy output values
into crisp, precise values. After processing fuzzy input values through a fuzzy logic system, the
output may be a fuzzy set representing a range of possible outcomes. Defuzzification is used to
select a single, precise output value from this fuzzy set, often by calculating the centroid or
center of gravity of the fuzzy set.

16. Distinguish between Supervised and Unsupervised ML algorithm.

In summary, supervised learning deals with labeled data and focuses on predicting target labels or outputs,
while unsupervised learning deals with unlabeled data and focuses on discovering patterns and structures
within the data. Both paradigms have their applications and are essential components of machine learning.

17. What is bias and give its importance in a NN model.

In summary, bias in a neural network model is essential for improving its flexibility, allowing it to learn and
generalize from the data more effectively. It adds a degree of freedom to the model, enabling it to capture
complex patterns and relationships that might not be possible without it.

18. What is Reinforcement learning? Give example.

A classic example of reinforcement learning is training an agent to play a game, such as the game of
chess or the game of Go:

 Agent: The neural network or algorithm responsible for making decisions (e.g., moves) in the
game.
 Environment: The game board and rules of the game.
 Actions: Possible moves that the agent can make on the game board.
 States: Different configurations of pieces on the game board.
 Rewards: Positive rewards for winning the game, negative rewards for losing, and possibly
intermediate rewards for making good moves or progressing toward winning.

19. Clustering is a technique in unsupervised machine learning used to group similar data points together
based on their intrinsic characteristics or features. The goal of clustering is to partition a dataset into subsets,
or clusters, such that data points within the same cluster are more similar to each other than to those in other
clusters. Clustering algorithms seek to identify natural groupings or patterns in the data without any prior
knowledge of the labels or classes.

20. What do mean by SVM model?

SVM stands for Support Vector Machine, which is a supervised machine learning algorithm used for
classification and regression tasks. SVMs are particularly well-suited for classification tasks in which the data
can be separated into two classes by finding the optimal hyperplane that maximizes the margin between the
classes.

You might also like