Proceedings of ELM 2021: Theory, Algorithms and Applications

Extreme learning machines (ELM) aim to enable pervasive learning and intelligence by combining machine learning and biological learning. ELM theories suggest that effective learning algorithms can be derived from randomly generated hidden neurons, as long as they are nonlinear, independent of training data, and application environments. Evidence from neuroscience suggests that similar principles apply in biological learning systems. The conference covers theoretical studies and practical applications of ELM, providing a glimpse of the latest advances in this field.

Format: Hardback
Length: 172 pages
Publication date: 19 January 2023
Publisher: Springer International Publishing AG

The 2021 International Conference on Extreme Learning Machine (ICELM) brought together experts from around the world to explore the cutting-edge of machine learning and artificial intelligence. With a focus on enabling pervasive learning and intelligence, the conference delved into the convergence of machine learning and biological learning, a topic that holds great promise for the future.

Extreme learning machines (ELM) are a novel approach to machine learning that aims to bridge the gap between traditional machine learning algorithms and biological learning systems. ELM theories propose that hidden neurons can be generated randomly or inherited from ancestors, and that effective learning algorithms can be derived from these neurons as long as they are nonlinear, piecewise continuous, and independent of training data and application environments.

One of the key insights of ELM theories is that "random hidden neurons" can capture an essential aspect of biological learning mechanisms. This is in contrast to traditional machine learning algorithms that rely on carefully tuned hidden neurons, which can be computationally expensive and difficult to optimize. By leveraging the power of randomness, ELM algorithms can achieve similar or even better performance than traditional algorithms, while also being more robust and scalable.

Evidence from neuroscience supports the principles of ELM. Studies have shown that the brain operates on a level of complexity that exceeds the capabilities of current computers. ELM theories suggest that this is because the brain uses random hidden neurons to learn and adapt, which allows it to make complex decisions and solve problems in real-time.

The conference covered a wide range of topics related to ELM, including theoretical studies, algorithms, and practical applications. Researchers presented their latest findings and discussed the challenges and opportunities associated with implementing ELM techniques in various fields, such as computer vision, natural language processing, and robotics.

One of the highlights of the conference was a panel discussion on the future of ELM and brain learning. The panelists, including leading researchers and industry experts, discussed the potential applications of ELM in fields such as healthcare, education, and transportation. They also discussed the ethical implications of using AI and machine learning, and the need for robust regulations and guidelines to ensure that these technologies are used responsibly and ethically.

Overall, the 2021 International Conference on Extreme Learning Machine was a successful event that brought together experts from diverse fields to explore the potential of machine learning and artificial intelligence. The conference provided a forum for academics, researchers, and engineers to share and exchange R&D experience on both theoretical studies and practical applications of the ELM technique and brain learning. As the field of AI continues to evolve, it is clear that ELM will play an increasingly important role in shaping the future of intelligent systems.

Weight: 442g
Dimension: 235 x 155 (mm)
ISBN-13: 9783031216770
Edition number: 1st ed. 2023