Welcome to our comprehensive course on NARX (Nonlinear AutoRegressive with eXogenous inputs) networks! This course is designed to provide a deep understanding of NARX networks, their significance, and practical implementation. Starting with an introduction to NARX networks, we explore their architecture, including input, hidden, and output layers, along with neuron configurations. Weight initialization techniques, hyperparameters like epochs and learning rates, and various activation and loss functions are covered extensively. You'll also learn about training methodologies such as Gradient Descent, Adam, and Stochastic Gradient Descent with Momentum. Practical sessions include data explanation, numerical examples, and implementation in MATLAB and Python, making this course essential for mastering NARX networks for real-world applications.
Why are NARX is important?
How do NARX works?
Architecture based on the input size
Xavier/Glorot Initialization
He Initialization
Scaled Random Initialization
Learning rate
Sigmoid
tanh
ReLU
MSE
RMSE
Entropy
MAE
Huber Loss
Gradient descent
Adam
SGDM
Data explanation
Python
Dr. Shrikant S. Jadhav is a distinguished academic with a robust educational background and extensive professional experience. He earned his Ph.D. in Electrical Engineering from North Carolina A&T State University. His dissertation focused on creating an environment for accessing remote field-programmable custom computing machine accelerators with multi-memory banks. Before this, he completed his Master of Technology in Information Technology at Bharati Vidyapeeth University, Pune, where he developed a scientific job submission grid service for his thesis. He also holds a Bachelor of Engineering in Computer Engineering from the University of Pune and worked on a project titled “Ext3 Explorer for Windows XP.”Professionally, Dr. Jadhav is an Assistant Professor in the Department of Electrical Engineering at San Jose State University (SJSU), where he has been since Fall 2021. At SJSU, he developed a new graduate course, EE277: Embedded Systems Design and teaches several courses, including EE178: Digital Design with FPGAs, EE176: Computer Hardware Design and Implementation and EE277A: Embedded SoC Design. He also advises and mentors both bachelor’s and master’s students on various projects and serves on the undergraduate curriculum and assessment committee. Dr. Jadhav has published research on mitigating urban heat islands and improving indoor thermal comfort with terrace gardens in Scientific Reports and on an extensible embedded processor for CNNs in the Hindawi Journal of Scientific Programming. His diverse expertise and commitment to education and research make him a valuable asset to the academic community.
Reviews
John Doe
Jane Smith
Michael Johnson
₹1000
₹6000
$12
$71
This course includes:
-
Validity:60 days
-
Validity:60 days
-
Category:Machine Learning
-
Lessons:12
-
Students:881
-
Language:English
-
Certificates:Yes
Payment details
NARX Neural Network
Better understanding with numerical examples and case studies.
