Scribd
Upload
16 views3 pages

DL Questions

The document outlines various topics related to Artificial Neural Networks, including fundamental concepts like artificial neurons, perceptrons, and the backpropagation algorithm. It also covers unsupervised learning networks, such as competitive learning networks and self-organizing maps, along with their applications. Additionally, the document introduces deep learning, discussing deep neural networks, their characteristics, challenges, and applications across different fields.

Uploaded by

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

DL Questions

The document outlines various topics related to Artificial Neural Networks, including fundamental concepts like artificial neurons, perceptrons, and the backpropagation algorithm. It also covers unsupervised learning networks, such as competitive learning networks and self-organizing maps, along with their applications. Additionally, the document introduces deep learning, discussing deep neural networks, their characteristics, challenges, and applications across different fields.

Uploaded by

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

UNIT-I: Artificial Neural Networks

2-Mark Questions:

1. What is an Artificial Neuron?

2. Define a Perceptron.

3. What is the role of the activation function in a neuron?

4. What is the difference between supervised and unsupervised learning?

5. What is the purpose of the backpropagation algorithm?

6. What is the key difference between a single-layer and a multi-layer


perceptron?

7. What are the limitations of a single-layer perceptron?

8. What is the role of the bias term in a neuron?

9. What is the difference between Hebbian learning and competitive


learning?

10. What are the applications of Hopfield networks?

5-Mark Questions:

1. Explain the architecture and working principle of a single-layer


perceptron.
2. Discuss its limitations and how they are addressed by multi-layer
perceptrons.
3. Describe the backpropagation algorithm in detail.
4. Explain the steps involved in training a feedforward neural network
using backpropagation.
5. Discuss the concept of associative memory.
6. Explain the working principle of Hopfield networks and their
applications in pattern recognition.
7. Compare and contrast the characteristics of supervised and
unsupervised learning. Provide examples of real-world applications for
each.
8. Explain the concept of the adaptive linear neuron (Adaline) and its
relationship to the perceptron.
9. Discuss the advantages and disadvantages of Adaline.
UNIT-II: Unsupervised Learning Network

2-Mark Questions:

1. What are competitive learning networks?


2. How does the Kohonen self-organizing map (SOM) work?
3. What is the purpose of learning vector quantization (LVQ)?
4. What is the difference between SOM and LVQ?
5. What is the principle of adaptive resonance theory (ART)?
6. What is the role of vigilance parameter in ART networks?
7. What are the applications of self-organizing maps?
8. How does Maxnet work?
9. What is the purpose of the Hamming network?
10. What are the limitations of competitive learning?

5-Mark Questions:

1. Explain the architecture and learning algorithm of the Kohonen self-


organizing map.
2. Discuss its applications in data visualization and clustering.
3. Describe the learning vector quantization (LVQ) algorithm.
4. Explain how it differs from the SOM and how it can be used for
classification.
5. Discuss the principles of adaptive resonance theory (ART).
6. Explain the architecture and learning process of an ART network.
7. Compare and contrast the characteristics of competitive learning
networks, such as Maxnet, Hamming network, and self-organizing maps.
8. Explain the role of unsupervised learning in artificial intelligence.
9. Discuss the applications of unsupervised learning techniques in areas
such as anomaly detection and dimensionality reduction.

UNIT-III: Introduction to Deep Learning

2-Mark Questions:

1. What is deep learning?


2. What are deep neural networks?
3. What are the key characteristics of deep learning models?
4. What is the role of representation learning in deep learning?
5. What are the different types of deep neural networks (e.g., CNN, RNN,
LSTM)?
6. What are the challenges of training deep neural networks?
7. What is the role of activation functions in deep learning?
8. What is the difference between shallow and deep neural networks?
9. What are the applications of deep learning?
10. What are the historical trends in deep learning research?

5-Mark Questions:

1. Discuss the key concepts and historical trends in deep learning


research.
2. Explain the architecture and working principle of deep feedforward
networks.
3. Discuss their applications in classification and regression.
4. Discuss the challenges of training deep neural networks, such as
vanishing/exploding gradients and overfitting.
5. Explain techniques to address these challenges.
6. Compare and contrast different types of deep neural networks, such as
convolutional neural networks (CNNs), recurrent neural networks
(RNNs), and long short-term memory (LSTM) networks.
7. Discuss the impact of deep learning on various fields, such as
computer vision, natural language processing, and artificial
intelligence.

You might also like