Xiaoli Li & Savitha Ramasamy 
TOWARDS HUMAN BRAIN INSPIRED LIFELONG LEARNING [EPUB ebook] 

Over the past few decades, the field of machine learning has made remarkable strides, surpassing human performance in tasks like voice and object recognition, as well as mastering various complex games. Despite these accomplishments, a critical challenge remains: the absence of general intelligence. Achieving artificial general intelligence (AGI) requires the development of learning agents that can continually adapt and learn throughout their existence, a concept known as lifelong learning.

In contrast to machines, humans possess an extraordinary capacity for continuous learning throughout their lives. Drawing inspiration from human learning, there is immense potential to enable artificial learning agents to learn and adapt continuously. Recent advancements in continual learning research have opened up new avenues to pursue this objective.

This book is a comprehensive compilation of diverse methods for continual learning, crafted by leading researchers in the field, along with their practical applications. These methods encompass various approaches, such as adapting existing paradigms like zero-shot learning and Bayesian learning, leveraging the flexibility of network architectures, and employing replay mechanisms to enable learning from streaming data without catastrophic forgetting of previously acquired knowledge.

This book is tailored for researchers, practitioners, and Ph D scholars working in the realm of Artificial Intelligence (AI). It particularly targets those envisioning the implementation of AI solutions in dynamic environments where data continually shifts, leading to challenges in maintaining model performance for streaming data.

Contents:

• Introduction (Chandan Gautam, Savitha Ramasamy, Suresh Sundaram and Li Xiaoli)


• Architectural Approaches to Continual Learning (Haytham M Fayek and Hong Ren Wu)


• Growing RBM on the Fly for Unsupervised Representation toward Classification and Regression (Savitha Ramasamy, Arul Murugan Ambikapathi and Kanagasabai Rajaraman)


• Lifelong Learning for Deep Neural Networks with Bayesian Principles (Cuong V Nguyen, Siddharth Swaroop, Thang D Bui, Yingzhen Li and Richard E Turner)


• Generative Replay-Based Continual Zero-Shot Learning (Chandan Gautam, Sethupathy Parameswaran, Ashish Mishra and Suresh Sundaram)


• Architect, Regularize and Replay: A Flexible Hybrid Approach for Continual Learning (Vincenzo Lomonaco, Lorenzo Pellegrini, Gabriele Graffieti and Davide Maltoni)


• Task-Agnostic Inference Using Base–Child Classifiers (Pranshu Ranjan Singh, Saisubramaniam Gopalakrishnan, Savitha Ramasamy and Arul Murugan Ambikapathi)


• Flashcards for Knowledge Capture and Replay (Saisubramaniam Gopalakrishnan, Pranshu Ranjan Singh, Haytham M Fayek, Savitha Ramasamy and Arul Murugan Ambikapathi)


• Reliable AI-Based Decision Support System for Chest X-Ray Classification Using Continual Learning (Theivendiram Pranavan and Arul Murugan Ambikapathi)

Readership: Researchers and Practitioners of AI Practitioners, who envision deployment of AI solutions in environments where the data is bound to drift and performance of the model drops for streaming data, Ph D scholars and researchers interested in research of Artificial General Intelligence.

Key Features:

• This book is a comprehensive compilation of diverse methods for continual learning, crafted by leading researchers in the field, along with their practical applications


• The primary aim of this book is to serve as a source of inspiration for future researchers, motivating them to explore and incorporate human-inspired principles into artificial intelligence, ultimately driving the realization of true AGI


• By delving into the innovative methods presented by leading researchers, you can gain a profound grasp of continual learning techniques and adaptation strategies for AI models