Index:
1. Explain model of a Neuron.
2. Explain Concept of feedback in neuron.
3. AI vs NN.
4. Single layered feed forward and multi layered feed forward
network architecture.
5. Recurrent networks.
6. Topologies.
7. Activation and synaptic dynamics.
8. Hebbian learning model.
9. Credit assignment problem.
10. Memory model.
11. Explain least mean square algorithm.
12. Explain back propagation algorithm.
13. Adalines and Madalines.
14. Explain how character recognition is done in ANN?
15. Application of pattern recognition.
16. Deep Learning overview and importance over machine
Learning.
17. Define ANN.
1. Explain model of a Neuron.
ANS-
2. Explain Concept of feedback in neuron.
ANS-
3. AI vs NN.
ANS-
Feature Neural Network (NN) Artificial Intelligence (AI)
Definition A computational model inspired by the A broad field of computer science
structure of the brain, composed of focused on creating intelligent
interconnected nodes (neurons) organized machines capable of human-like
in layers. tasks.
Function Processes data, learns patterns, and makes Aims to create machines capable of
predictions. simulating human intelligence.
Scope Specific technique for pattern recognition Encompasses a wide range of
and learning from data. techniques and technologies for
various intelligent tasks.
Applications Used in image and speech recognition, Applied in robotics, autonomous
pattern detection, etc. vehicles, language translation, etc.
Learning Learns from data by adjusting connection Involves learning from data,
Mechanism strengths (weights). making decisions, and adapting to
tasks.
Examples Deep learning networks like CNNs, Machine learning algorithms,
RNNs, GANs, etc. expert systems, robotics, chatbots,
etc.
4. Single layered feed forward and multi layered feed forward network architecture.
ASN-
5. Recurrent networks.
ANS-
6. Topologies.
ANS-
7. Activation and synaptic dynamics.
8. Hebbian learning model.
9. Credit assignment problem.
10. Memory model.
11. Explain least mean square algorithm.
12. Explain back propagation algorithm.
13. .
Adalines and Madalines - Algorithm and Applications:
4. Adalines and Madalines:
• Adaline (Adaptive Linear Neuron) and Madaline (Multiple Adalines) are early
neural network models.
• Adaline:
• Uses a linear activation function and adjusts weights based on the difference
between the predicted and actual outputs.
• It aims to minimize the error by adjusting weights in the direction that
reduces the error.
• Applications include pattern recognition, signal processing, and linear
classification tasks.
• Madaline:
• Utilizes multiple Adalines in layers for more complex tasks.
• Employs multiple linear neurons arranged in layers, enabling it to handle
more intricate patterns.
• Applications include multi-class classification and pattern recognition tasks.
14. Explain how character recognition is done in ANN.
15. Application of pattern recognition.
ANS-
1. Speech Recognition:
• Application: Voice-activated virtual assistants (e.g., Siri, Alexa),
transcription services, and interactive voice response systems.
• Use: Recognizing and transcribing spoken language into text or
commands.
2. Biometric Identification:
• Application: Fingerprint recognition, iris scanning, and facial
recognition for security and access control.
• Use: Verifying and identifying individuals based on unique biological or
behavioral characteristics.
3. Medical Diagnosis:
• Application: Disease diagnosis through medical imaging (MRI, CT
scans), pathology analysis, and patient monitoring.
• Use: Identifying patterns indicative of diseases, tumors, or abnormalities
in medical data.
4. Natural Language Processing (NLP):
• Application: Sentiment analysis, chatbots, language translation, and
speech-to-text systems.
• Use: Understanding and processing human language patterns for various
applications in communication and information retrieval.
5. Gesture Recognition:
• Application: Human-computer interaction, virtual reality, and robotics.
• Use: Recognizing and interpreting hand or body movements as input
commands for devices or applications.
6. Autonomous Vehicles:
• Application: Object detection, pedestrian recognition, and road sign
recognition in self-driving cars.
• Use: Analyzing patterns in sensor data to make real-time decisions for
safe navigation.
16. Deep Learning overview and importance over machine Learning.
Deep learning is a method in artificial intelligence (AI) that teaches computers to process data in
a way that is inspired by the human brain. Deep learning models can recognize complex patterns
in pictures, text, sounds, and other data to produce accurate insights and predictions.
The components of a deep neural network are the following.
Input layer
An artificial neural network has several nodes that input data into it. These nodes make up the
input layer of the system.
Hidden layer
The input layer processes and passes the data to layers further in the neural network. These hidden
layers process information at different levels, adapting their behavior as they receive new
information. Deep learning networks have hundreds of hidden layers that they can use to analyze
a problem from several different angles.
Output layer
The output layer consists of the nodes that output the data. Deep learning models that output "yes"
or "no" answers have only two nodes in the output layer.
A deep learning network has the following benefits over traditional machine learning.
Efficient processing of unstructured data
Machine learning methods find unstructured data, such as text documents, challenging to process
because the training dataset can have infinite variations. On the other hand, deep learning models
can comprehend unstructured data and make general observations without manual feature
extraction. For instance, a neural network can recognize that these two different input sentences
have the same meaning:
• Can you tell me how to make the payment?
• How do I transfer money?
Hidden relationships and pattern discovery
A deep learning application can analyze large amounts of data more deeply and reveal new
insights for which it might not have been trained.
Unsupervised learning
Deep learning models can learn and improve over time based on user behavior. They do not
require large variations of labeled datasets.
Volatile data processing
Volatile datasets have large variations. One example is loan repayment amounts in a bank. A deep
learning neural network can categorize and sort that data as well, such as by analyzing financial
transactions and flagging some of them for fraud detection.
17. Define ANN.
ANS- An artificial neural network (ANN) is a mathematical model that mimics the
way nerve cells work in the human brain. It is a type of machine learning process
called deep learning.
