CSL465: Neural Networks - Group 19 Hopfield Neural Network (HNN) - NIT Delhi (2022 Batch)
This is a PowerPoint Presentation on Hopfield Neural Networks. It is part of our Peer Learning Session (PLS-1) for the course on Neural Networks (CSL465) taken by our Professor Dr. Chandra Prakash at NIT Delhi.
A Hopfield network (or Ising model of a neural network or Ising–Lenz–Little model) is a form of recurrent artificial neural network and a type of spin glass system popularized by John Hopfield in 1982 as described earlier by Little in 1974 based on Ernst Ising's work with Wilhelm Lenz on the Ising model.
A Hopfield network is a single-layered and recurrent network in which the neurons are entirely connected, i.e., each neuron is associated with other neurons.
A Hopfield network is trained to store various patterns or memories and afterward, it is ready to recognize any of the learned patterns by uncovering partial or even some corrupted data about that pattern, i.e., it eventually settles down and restores the closest pattern.
Thus, like the human brain, the Hopfield model has stability in pattern recognition.
Base Paper: https://bi.snu.ac.kr/Courses/g-ai09-2...
Other Paper: https://cogsci.ucsd.edu/~sereno/107B/...
We are B.Tech (Batch 2022) Undergraduates from the branches: Electrical and Electronics Engineering (EEE) and Electronics and Communication Engineering (ECE).
Credits for the video:
Dr. Chandra Prakash (Professor and Course Instructor - CSL465)
Aswin Chowdary Undavalli (181230009, ECE)
Bajjuri Pavan Kumar (181230010, EEE)
Rohan Prasad (181230042, EEE)
U.S Sreekash (181230055, EEE)
I would like to take this opportunity to thank Dr. Chandra Prakash for his unflinching support and guidance which helped us in creating and uploading this work. Also, a special mention to my team members - Aswin, Bajjuri Pavan and U.S Sreekash for being a wonderful and creative team.
Kindly watch the whole video and make sure you share your insights and suggestions in the comments.
Leave a like if you found this video useful.