Electronic Synthesis of the Avian Retina

Uemura, M.; Viglione, S. S.

doi:10.1109/tbme.1968.4502558

Cited by 18 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others followed with simple electronic models of neural processes [Lew68][JH69], [Roy72] [Bro79]. On the larger scale, Runge [RUV68] built a fairly detailed model of the pigeon retina using 145 Cadmium Sulphide sensors and 381 neural analogue circuits taking up 50 circuit boards. Early electrical models of the cochlea are discussed in [KS59], including a transmission line of 178 sections, with each section comprising two inductors and four capacitors.…”

Section: Early Forms Of Neuromorphic Systems: Systems Built From Discmentioning

confidence: 99%

Neuromorphic Systems: Past, Present and Future

Smith

2009

Advances in Experimental Medicine and Biology

View full text Add to dashboard Cite

Neuromorphic systems are implementations in silicon of elements of neural systems. The idea of electronic implementation is not new, but modern microelectronics has provided opportunities for producing systems for both sensing and neural modelling that can be mass produced straightforwardly. We review the the history of neuromorphic systems, and discuss the range of neuromorphic systems that have ben developed. We discuss recent ideas for overcoming some of the problems, particularly providing effective adaptive synapses in large numbers.

show abstract

Section: Early Forms Of Neuromorphic Systems: Systems Built From Discmentioning

confidence: 99%

Neuromorphic Systems: Past, Present and Future

Smith

2009

Advances in Experimental Medicine and Biology

View full text Add to dashboard Cite

show abstract

“…Modern neural hardware developers are primarily interested in chip-based implementation. This has certainly made the resulting hardware smaller (the neural model of the avian retina developed by Runge et al [49] ran to 50 circuit boards! ), though more difficult to test and modify.…”

Section: Techniques For Hardware Implementationmentioning

confidence: 99%

Implementing Neural Models in Silicon

Smith

Handbook of Nature-Inspired and Innovative Computing

View full text Add to dashboard Cite

Neural models are used in both computational neuroscience and in pattern recognition. The aim of the first is understanding of real neural systems, and of the second is gaining better, possibly brain-like performance for systems being built. In both cases, the highly parallel nature of the neural system contrasts with the sequential nature of computer systems, resulting in slow and complex simulation software. More direct implementation in hardware (whether digital or analogue) holds out the promise of faster emulation both because hardware implementation is inherently faster than software, and because the operation is much more parallel. There are costs to this: modifying the system (for example to test out variants of the system) is much harder when a full application specific integrated circuit has been built. Fast emulation can permit direct incorporation of a neural model into a system, permitting realtime input and output. Appropriate selection of implementation technology can help to make interfacing the system to external devices simpler. We review the technologies involved, and discuss some example systems. Why implement neural models in silicon?There are two primary reasons for implementing neural models: one is to attempt to gain better, and possibly brain-like performance for some system, and the other is to study how some particular neural model performs. Current computer systems do not approach brain-like system performance in many areas (sensing, motor control, and pattern recognition, for example, to say nothing of the higher level capabilities of mammalian brains). There has been considerable research into how the neural system attains its capabilities. Implementing neural systems in silicon can permit direct applications of this research by permitting neural models to run rapidly enough to be applied directly to data. It is true that increases in workstation performance have allowed some software implementations of neural models to run in real time, but the highly parallel nature of neural systems, coupled with increasing interest in the application of more sophisticated (and computationally more expensive) neural models has caused interest in more direct implementation to be maintained. Interest in applying neural models to sensory and sensory-motor systems has made attaining real-time performance a critical factor. Real sensory systems are highly parallel, with multiple parallel channels of information, so that even though each channel might be implementable in real-time in software, implementing multiple channels implies hardware implementation.The study of how particular models of neural systems perform is one aspect of computational neuroscience. Such studies are usually carried out in software, as this allows easy alteration of and experimentation with systems. However, models of the highly parallel architecture of neural systems run slowly on standard 1

show abstract

“…Then some simple equivalent circuits were introduced for neuron model [12], [13], [14], [15]. On the other hand, first large scale Neuromorphic circuit was an electrical simulation of pigeon retina in 1968 [16]. [17] discussed a fairly large electrical model for the cochlea with a transmission line connecting 178 different sections and every section included four capacitors and two inductors.…”

Section: Introductionmentioning

confidence: 99%

“…14 also shows the edge connectivity results for different velocities. We lose significant parts of the boundary for velocities16 and Global Velocity and Edge Estimation in Event-Based Videos 81 (a) Estimated magnitudes for different velocities (b) Estimated directions for different velocities…”

mentioning

confidence: 99%

Analysis of object and its motion in event-based videos

Seifozzakerini¹

View full text Add to dashboard Cite

This thesis would not be possible if I did not have the help and advice of several people who contributed their valuable support in completion of this study. First of all, I would like to express my sincere appreciation and gratitude to my supervisor, Associate Professor Mao Kezhi for giving me an opportunity to pursue my interest in research work under his valuable guidance. He is not only a supervisor but also a warm hearted friend that I always can count on his support and help. It gives me immense pleasure to thank my mentor and co-supervisor, Doctor Yau Wei-Yun for his support, continuous guidance and astute criticism during this study. Nothing can gratify the invaluable time he generously dedicated to me despite his busy schedule. My special thanks go to my Thesis Advisory Committee members, Professor Huang Guangbin, Associate Professor Wang Han and Dr. Li Xiaoli for their invaluable guidance and encouragement throughout my research. Financial assistance provided by the Agency for Science, Technology and Research (A*STAR) in the form of Graduate Scholarship is thankfully acknowledgeable. I would like to express my gratitude to the staffs in Institute for Infocomm Research (I2R), Ms. Janice Lee Sze Min and Ms. Felicia Chew for their effort on my attachment matters. I cannot miss mentioning my home mates during last 4 years in Singapore, Amin Kianinejhad, Siavash Sakhavi, Hossein Dehghani Tafti and Ali Rajabipoor for making ii my life during Ph.D. a very memorable one. Also, I should mention my Iranian friends in Singapore, whom their moral supports were a great help during this candidature:

show abstract

Electronic Synthesis of the Avian Retina

Cited by 18 publications

References 10 publications

Neuromorphic Systems: Past, Present and Future

Neuromorphic Systems: Past, Present and Future

Implementing Neural Models in Silicon

Analysis of object and its motion in event-based videos

Contact Info

Product

Resources

About