Biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and others were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classes such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. In addition, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the

Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing -data processing domains in which humans have long held clear advantages over conventional algorithms. In contrast to biological neural systems, which are capable of learning continuously, deep artificial networks have a limited ability for incorporating new information in an already trained network. As a result, methods for continuous learning are potentially highly impactful in enabling the application of deep networks to dynamic data sets. Here, inspired by the process of adult neurogenesis in the hippocampus, we explore the potential for adding new neurons to deep layers of artificial neural networks in order to facilitate their acquisition of novel information while preserving previously trained data representations. Our results on the MNIST handwritten digit dataset and the NIST SD 19 dataset, which includes lower and upper case letters and digits, demonstrate that neurogenesis is well suited for addressing the stability-plasticity dilemma that has long challenged adaptive machine learning algorithms.

Robotic systems are often very complex and diflcult to operate, especially as multiple robots are integrated to accomplish diflcult tasks. In addition, training the operators of these complex robotic systems is timeconsuming and costly. In this paper, a virtual reality based robotic control system is presented. The virtual realiy system provides a means by which operators can operate, and be trained to operate, complex robotic Jystems in an intuitive, cost-effective way, Operator interaction with the robotic system is at a high, taskoriented, level. Continuous state monitoring prevents illegal robot actions and provides interactive feedback to the operator and real-time training for novice users.

This paper describes a general methodological framework for evaluating the perceptual properties of auditory stimuli. The framework provides analysis techniques that can ensure the effective use of sound for a variety of applications including virtual realit) and data sonification systems. Specifically, we discuss data collection techniques for the perceptual qualities of single auditory stimuli including identification tasks, context-based ratings, and attribute ratings. In adllition, we present methods for comparing auditory stimuli, such as discrimination tasks, similarity ratings, and sorting tasks. Finally, we discuss statistical techniques that focus on the perceptual relations among stimuli, such as Multidimensional Scaling (MDS) and Pathfinder kialysis. These methods are presented as a staring point for an organized and systematic approach for non-experts in perceptual experimental methods, rather than as a complete manual for performing the statistical techniques and data collection methods. It is our hope that this paper will help foster further interdisciplinary collaboration among perceptual researchers, designers, engineers, and others in the development of effective auditory displays.

This paper addresses two main issues concerning virtual acoustic displays. First, we discuss the computational requirements including sound generation (or synthesis), environmental effects modeling, and three-dimensional (3-D) sound localization. The computational analysis reveals that acoustic processing delays of at least 66 ms are expected with today's technology. This analysis motivates the second issue: how much computational time is available for executing the acoustic process, assuming the requirement for perceptually perfect audiovisual synchronization? A psychoacoustic experiment designed to quantify the tolerable audiovisual delay indicates that an acoustic impact event must occur within an average of 175 ms of the visual event in order for the events to be perceived as synchronous. The most highly trained observers detect desynchrony with an audiovisual delay as low as 100 ms. The results of the computational requirement analysis and the psychoacoustic synchronization experiment provide important information for designers and researchers of virtual acoustic displays.

No abstract

Neural-inspired spike-based computing machines often claim to achieve considerable advantages in terms of energy and time efficiency by using spikes for computation and communication. However, fundamental questions about spike-based computation remain unanswered. For instance, how much advantage do spike-based approaches have over conventional methods, and under what circumstances does spike-based computing provide a comparative advantage? Simply implementing existing algorithms using spikes as the medium of computation and communication is not guaranteed to yield an advantage. Here, we demonstrate that spike-based communication and computation within algorithms can increase throughput, and they can decrease energy cost in some cases. We present several spiking algorithms, including sorting a set of numbers in ascending/descending order, as well as finding the maximum or minimum or median of a set of numbers. We also provide an example application: a spiking median-filtering approach for image processing providing a low-energy, parallel implementation. The algorithms and analyses presented here demonstrate that spiking algorithms can provide performance advantages and offer efficient computation of fundamental operations useful in more complex algorithms.

No abstract