Neural inference at the frontier of energy, space, and time.

Computing, since its inception, has been processor-centric, with memory separated from compute. Inspired by the organic brain and optimized for inorganic silicon, NorthPole is a neural inference architecture that blurs this boundary by eliminating off-chip memory, intertwining compute with memory on-chip, and appearing externally as an active memory chip. NorthPole is a low-precision, massively parallel, densely interconnected, energy-efficient, and spatial computing architecture with a co-optimized, high-utilization programming model. On the ResNet50 benchmark image classification network, relative to a graphics processing unit (GPU) that uses a comparable 12-nanometer technology process, NorthPole achieves a 25 times higher energy metric of frames per second (FPS) per watt, a 5 times higher space metric of FPS per transistor, and a 22 times lower time metric of latency. Similar results are reported for the Yolo-v4 detection network. NorthPole outperforms all prevalent architectures, even those that use more-advanced technology processes.

Sound Source Localization through 8 MEMS Microphones Array Using a Sand-Scorpion-Inspired Spiking Neural Network.

Sand-scorpions and many other arachnids perceive their environment by using their feet to sense ground waves. They are able to determine amplitudes the size of an atom and locate the acoustic stimuli with an accuracy of within 13° based on their neuronal anatomy. We present here a prototype sound source localization system, inspired from this impressive performance. The system presented utilizes custom-built hardware with eight MEMS microphones, one for each foot, to acquire the acoustic scene, and a spiking neural model to localize the sound source. The current implementation shows smaller localization error than those observed in nature.

High Spin Polarization at Ferromagnetic Metal-Organic Interfaces: A Generic Property.

A high spin polarization of states around the Fermi level, EF, at room temperature has been measured in the past at the interface between a few molecular candidates and the ferromagnetic metal Co. Is this promising property for spintronics limited to these candidates? Previous reports suggested that certain conditions, such as strong ferromagnetism, i.e., a fully occupied spin-up d band of the ferromagnet, or the presence of π bonds on the molecule, i.e., molecular conjugation, needed to be met. What rules govern the presence of this property? We have performed spin-resolved photoemission spectroscopy measurements on a variety of such interfaces. We find that this property is robust against changes to the molecule and ferromagnetic metal's electronic properties, including the aforementioned conditions. This affirms the generality of highly spin-polarized states at the interface between a ferromagnetic metal and a molecule and augurs bright prospects toward integrating these interfaces within organic spintronic devices.

Do audio-visual motion cues promote segregation of auditory streams?

An audio-visual experiment using moving sound sources was designed to investigate whether the analysis of auditory scenes is modulated by synchronous presentation of visual information. Listeners were presented with an alternating sequence of two pure tones delivered by two separate sound sources. In different conditions, the two sound sources were either stationary or moving on random trajectories around the listener. Both the sounds and the movement trajectories were derived from recordings in which two humans were moving with loudspeakers attached to their heads. Visualized movement trajectories modeled by a computer animation were presented together with the sounds. In the main experiment, behavioral reports on sound organization were collected from young healthy volunteers. The proportion and stability of the different sound organizations were compared between the conditions in which the visualized trajectories matched the movement of the sound sources and when the two were independent of each other. The results corroborate earlier findings that separation of sound sources in space promotes segregation. However, no additional effect of auditory movement per se on the perceptual organization of sounds was obtained. Surprisingly, the presentation of movement-congruent visual cues did not strengthen the effects of spatial separation on segregating auditory streams. Our findings are consistent with the view that bistability in the auditory modality can occur independently from other modalities.

Multimodal integration of micro-Doppler sonar and auditory signals for behavior classification with convolutional networks.

The ability to recognize the behavior of individuals is of great interest in the general field of safety (e.g. building security, crowd control, transport analysis, independent living for the elderly). Here we report a new real-time acoustic system for human action and behavior recognition that integrates passive audio and active micro-Doppler sonar signatures over multiple time scales. The system architecture is based on a six-layer convolutional neural network, trained and evaluated using a dataset of 10 subjects performing seven different behaviors. Probabilistic combination of system output through time for each modality separately yields 94% (passive audio) and 91% (micro-Doppler sonar) correct behavior classification; probabilistic multimodal integration increases classification performance to 98%. This study supports the efficacy of micro-Doppler sonar systems in characterizing human actions, which can then be efficiently classified using ConvNets. It also demonstrates that the integration of multiple sources of acoustic information can significantly improve the system's performance.