Brains and Machines

Dr. Charlotte Frenkel from the Technical University of Delft set records with a low-power neuromorphic chip she designed as part of her Ph.D. In this episode of Brains and Machines, she talks to Dr. Sunny Bains of University College London about what she has learned about building simplicity into chips and integrity into benchmarks. Discussion follows with Dr. Giulia D’Angelo from the Czech Technical University in Prague and Professor Ralph Etienne-Cummings of Johns Hopkins University.

Dharmendra Modha’s TrueNorth chip added the word neuromorphic to the technorati lexicon back in 2014. In this episode of Brains and Machines, he talks to Dr. Sunny Bains of University College London about how that project led to his work on NorthPole and the axiomatic approach he took to design. Discussion follows with Dr. Giulia D’Angelo from the Czech Technical University in Prague and Professor Ralph Etienne-Cummings of Johns Hopkins University.

For 50 years Dr. Terry Sejnowski has modelled the brain and used his insights to help inform AI. In this episode of Brains and Machines, he talks to Dr. Sunny Bains of the University College London about how information flows both ways between neuroscience and engineered intelligence, proposes a new way of looking at memory and considers the Hopfield-Hinton Nobel Prize. Discussion follows with Dr. Giulia D’Angelo from the Czech Technical University in Prague and Professor Ralph Etienne-Cummings of Johns Hopkins University.

Dr. Jennifer Hasler of Georgia Tech is best known for her work with field programmable analog arrays (FPAAs). In this episode of Brains and Machines, she talks about the importance of, and progress in, analog electronics for AI with Dr. Sunny Bains of the University College London. Discussion follows with Dr .Giulia D’Angelo from the Czech Technical University in Prague and Professor Ralph Etienne-Cummings of Johns Hopkins University.

Tony Lewis, the CTO of BrainChip, shares insights on groundbreaking neuromorphic technology. He discusses the strategic evolution of BrainChip's AI focus, emphasizing the innovative Temporal Event-Based Neural Networks that enhance efficiency. The conversation delves into the Akida chip's future iterations and its role in advanced AI applications, especially for autonomous driving. Additionally, the advantages of recurrent neural networks and event-based processing are explored, showcasing their potential in real-time prediction and parallel processing for cutting-edge neural applications.

Rodney Brooks, an Emeritus Professor at MIT and CTO of Robust AI, discusses the evolution of robotics and AI. He emphasizes the shift from traditional AI to innovative biologically-inspired designs. The conversation highlights the importance of physical intelligence in robots and reviews the challenges they face in learning tasks. Brooks critiques the current limitations of artificial systems compared to human capabilities, advocating for the integration of physical interactions in developing more advanced and human-like robots.

Katie Schuman, a Professor at the University of Tennessee, Knoxville, shares her insights on neuromorphic computing and evolutionary approaches in neural processing. She discusses her journey from computer science to this groundbreaking field, emphasizing the integration of spiking neural networks and evolutionary algorithms. The conversation highlights advancements in neuromorphic systems, including their efficiency and the challenges of training them. Schuman also touches on the role of community, open-source frameworks, and the future potentials of robotic applications.

Sumeet Kumar, Founder and CEO of Innatera, shares insights into their innovative spiking neural network chip tailored for sensor applications. Petrut Bogdan, Neuromorphic Architect, discusses the intricate design choices and challenges faced in creating this versatile chip. They explore the importance of energy efficiency, the integration of analog and digital neurons, and the potential for low-power applications in healthcare. Their conversation touches on the future of accessible neuromorphic engineering and the role of these technologies in enhancing smart devices.

In this episode of Brains and Machines, UCL’s Sunny Bains talks parallelism, neural net efficiency and risk taking with Caltech’s Prof. Carver Mead. Now an emeritus professor, Mead has been instrumental in the development of chip design, and was one of the first employees of Noyce and Moore, which later became Intel. He’s also one of the founders of the field of neuromorphic engineering. Discussion follows with Dr. Giulia D’Angelo Marie Curie Fellow at The Czech Technical University in Prague, and Professor Ralph Etienne-Cummings of Johns Hopkins University.

In this special episode of the Brains and Machines podcast, Dr. Sunny Bains and Dr. Giulia D’Angelo talk to four early career researchers: Dr. Kenneth Stewart, a computer scientist at the U.S. Naval Research Laboratory in Washington DC; Dr. Laura Kriener, a postdoctoral researcher at The University of Bern in Switzerland; Jens Pedersen, a Ph.D. student at The Royal Institute of Technology (KTH) in Stockholm, Sweden; and Dr. Fabrizio Ottati, an AI/ML computer architect at NXP Semiconductors in Hamburg, Germany. They discuss learning rules for spiking neural networks, primitives for computations on neuromorphic hardware, and the benefits and drawbacks of neuromorphic engineering.