Local STDP modules enable label-efficient event-camera detection with 78.6% mAP on drone benchmarks and better drift handling than k-means.
Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter running on more conventional hardware devices including a CPU, a GPU, Nvidia's Jetson TX1, and the Movidius Neural Compute Stick. Our results indicate that for this inference application, Loihi outperforms all of these alternatives on an energy cost per inference basis while maintaining equivalent inference accuracy. Furthermore, an analysis of tradeoffs between network size, inference speed, and energy cost indicates that Loihi's comparative advantage over other low-power computing devices improves for larger networks.
verdicts
UNVERDICTED 3representative citing papers
Spiking neuron grid on Loihi solves CDO asset allocation with greater than 99.9 percent accuracy and over 1000 times speedup versus conventional methods.
Authors apply a consistent methodology to benchmark physical performance metrics across neural network architectures and device technologies, identifying promising combinations.
citing papers explorer
-
Brain-inspired spike-timing plasticity for reliable label-efficient event-camera vision
Local STDP modules enable label-efficient event-camera detection with 78.6% mAP on drone benchmarks and better drift handling than k-means.
-
High Speed Cognitive Domain Ontologies for Asset Allocation Using Loihi Spiking Neurons
Spiking neuron grid on Loihi solves CDO asset allocation with greater than 99.9 percent accuracy and over 1000 times speedup versus conventional methods.
-
Benchmarking Physical Performance of Neural Inference Circuits
Authors apply a consistent methodology to benchmark physical performance metrics across neural network architectures and device technologies, identifying promising combinations.