KEMBAR78
L019 ML Exp10 | PDF | Artificial Neural Network | Computational Neuroscience
Scribd
Upload
39 views2 pages

L019 ML Exp10

The document summarizes a research paper on artificial neural networks (ANNs) and their applications in forecasting. It begins by highlighting the importance of understanding different ANN types and architectures. The paper then discusses the development of ANNs, including their structure and typical procedural steps. It proposes several ANN models for forecasting solar irradiance, rainfall, and temperature. The paper also analyzes the training process of an Improved Backpropagation Neural Network for rainfall forecasting. Overall, the document provides insights into ANNs and their use in addressing complex forecasting problems through learning from historical data.

Uploaded by

Burhanuddin Bohra
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
39 views2 pages

L019 ML Exp10

The document summarizes a research paper on artificial neural networks (ANNs) and their applications in forecasting. It begins by highlighting the importance of understanding different ANN types and architectures. The paper then discusses the development of ANNs, including their structure and typical procedural steps. It proposes several ANN models for forecasting solar irradiance, rainfall, and temperature. The paper also analyzes the training process of an Improved Backpropagation Neural Network for rainfall forecasting. Overall, the document provides insights into ANNs and their use in addressing complex forecasting problems through learning from historical data.

Uploaded by

Burhanuddin Bohra
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/ 2

SVKM’s NMIMS

Mukesh Patel School of Technology Management & Engineering


Program:
Course:
Practical .10
PART A
(PART A : TO BE REFFERED BY STUDENTS)

A.1 Aim: Study of recent research paper on Neural Network Algorithm.

A.2 Prerequisite:
Understanding of forward and back propagation, Activation function

A.3 Outcome:
After successful completion of this experiment students will be able to:
Understand the working of Neural Network and its application

A.4

Research Paper summary must include following details:

Introduction

Methodology

Advantages

Limitations

Applications

Future scope

References
PART B

(PART B: TO BE COMPLETED BY STUDENTS)

Roll No. L019 Name: Kaunchi Jain


Class: BTech CSDS 311 Batch: B1
Date of Experiment: Date of Submission:
Grade:

B.1 Paper Summary:

The paper provides a comprehensive analysis of artificial neural network (ANN) architecture, types, and
their applications in forecasting. The paper aims to give a clear understanding of the comparison between
the human brain and artificial intelligence, discuss the development background of ANN, and propose
various types of ANN for forecasting applications.

The paper begins by highlighting the importance of understanding the primary types and applications of
ANN. It discusses the development background of ANN, including its generalized procedural steps and
typical structure, along with various applications. The authors propose different types of ANN, such as
multilayer perceptron neural network, improved backpropagation neural network, and Elman neural
network, for forecasting solar irradiance, rainfall, and temperature, respectively.

The paper emphasizes the significance of ANN in addressing complex problems efficiently and its
resemblance to brain activities. It provides valuable information about different ANN architectures, types,
merits, and demerits. The proposed ANN-based forecasting models are analysed and validated using real-
time meteorological data, achieving rigorous results with reduced errors.

In conclusion, the paper contributes to enriching knowledge about ANN and its research. It provides
insights into the history, architecture, types, and applications of ANN. The proposed forecasting models
demonstrate the effectiveness of ANN in addressing forecasting challenges. The paper serves as a valuable
resource for students and researchers interested in ANN and its applications.

It also discusses forward and backpropagation in the context of artificial neural networks
(ANNs). It mentions the proposed Improved Backpropagation Neural Network (IBPNN) for
rainfall forecasting, which utilizes a momentum-based backpropagation learning algorithm.
The paper describes the training stages of the IBPNN, including the feedforward stage, error
computation stage, and weight modification and update stage. It also explains how the error is
propagated backward from the output layer to the hidden layer and input layer during the
backpropagation stage. The document provides mathematical equations for the synaptic
weight updating process in the IBPNN, which involve the use of gradient descent with
momentum and an adaptive linear backpropagation training algorithm. Overall, the paper
discusses the implementation and significance of both forward and backpropagation in the
context of ANN-based forecasting models.

B.2 Conclusion:

I am now able to:


Understand the working of Neural Network and its application

You might also like