Neuromorphic computing .pdf
- 1. NEUROMORPHIC COMPUTING Presented by: MOHANA PRIA R NARMADHA NITHI R GOVERNMENT COLLEGE OF TECHNOLOGY- COIMBATORE. DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING
- 2. • What is neuromorphic computing? • How does it work? • Biological neuron Vs artificial neuron • Impact in solving today’s problems • Comparison between traditional AI and neuromorphic computing • Future prediction / Applications • Limitations OVERVIEW 1
- 3. • Neuromorphic computing is based on the principles of neural networks and aims to develop hardware and software systems that mimic the architecture and function of the human brain. • Inspired by the human brain and neural network principles, and has recently gained prominence due to advancements in Artificial Intelligence. WHAT IS NEUROMORPHIC COMPUTING? 2
- 4. HOW IT WORKS? • Neuromorphic computing circuits are designed that incorporate both digital and analog components to emulate the way biological neurons and synapses interact with one another. • Employs a distinct high performance architecture. • Spiking neural network (SNN) is the prevalent type of neuromorphic hardware 3
- 5. BIOLOGICAL NEURON ARTIFICIAL NEURON • Input • Node • Output • Interconnections BIOLOGICAL NEURON VS ARTIFICIAL NEURON • Dendrites • Cell Nucleus (Soma) • Axis • Synapse 4
- 6. • To revolutionize AI computing by allowing AI algorithms to run at the edge instead of the cloud due to their, • smaller size and • low power consumption • With the ability to adapt to its environment IMPACT IN SOLVING TODAY’S PROBLEMS 5
- 7. TRADITIONAL AI NEUROMORPHIC COMPUTING • Uses a non-von Neumann architecture • Learn from unsupervised data • Systems that closely mimic human brain • Use a von Neumann architecture • Labelled data to learn • Run on conventional computer systems TRADITIONAL AI VS NEUROMORPHIC COMPUTING 6
- 8. • Microcombs • Chip manufacturing • Driverless cars • Drones • Robots • Smart home devices • Natural language, speech and image processing • Data analytics APPLICATIONS 7
- 9. • Powerful tool for solving problems that are currently beyond our grasp. • Enhance the learning capabilities of the devices • Making them smarter • More efficient • Mimics the neuron spiking functions of biological nervous systems BENEFITS 8
- 10. • Limited accessibility for non-experts • Ethical and legal issues surrounding sentient machines • Current constraints based on our understanding of human cognition • Limited accuracy • Lack of standardized benchmarks • Underdeveloped software algorithms LIMITATIONS 9
- 11. THANK YOU!