DOI: https://doi.org/10.29363/nanoge.neumatdecas.2023.051
Publication date: 9th January 2023
Artificial neural networks (ANNs) with rectified linear units (ReLUs) are standard in solving many artificial intelligence (AI) tasks and pretrained weights are often available. Spiking neural networks (SNNs) offer a potential for energy efficient neuromorphic implementation, however the training of such networks is challenging. In this work we show that fully-connected ReLU and single-spike SNNs are equivalent. Let’s assume that we have pretrained weights and biases of a fully-connected ReLU network with L layers. The real value coming to the input of the ANN is converted to the spiking time which is sent to the spiking neural network implementing a specific non-leaky integrate-and-fire dynamics with linear postsynaptic potential and positive integration bias. Each neuron spikes at time when its membrane potential reaches the predefined threshold after which a very long refractory period is assumed making sure that the neuron stays silent. All neurons that don’t spike before some observation time are forced to spike. The parameters of SNN are set according to our mapping function such that the activity of the neuron in ReLU network can be recovered from the timing of the spike from the corresponding neuron in the SNN. Due to the theoretical equivalence between the two networks it is possible to perform the energy efficient SNN classification of the MNIST dataset with the exact same perfomance as pretrained ReLU network and without any additional training or fine-tuning.
nanoGe is a prestigious brand of successful science conferences that are developed along the year in different areas of the world since 2009. Our worldwide conferences cover cutting-edge materials topics like perovskite solar cells, photovoltaics, optoelectronics, solar fuel conversion, surface science, catalysis and two-dimensional materials, among many others.
Previously nanoGe Spring Meeting (NSM) and nanoGe Fall Meeting (NFM), MATSUS is a multiple symposia conference focused on a broad set of topics of advanced materials preparation, their fundamental properties, and their applications, in fields such as renewable energy, photovoltaics, lighting, semiconductor quantum dots, 2-D materials synthesis, charge carriers dynamics, microscopy and spectroscopy semiconductors fundamentals, etc.
International Conference on Hybrid and Organic Photovoltaics
International Conference on Hybrid and Organic Photovoltaics (HOPV) is celebrated yearly in May. The main topics are the development, function and modeling of materials and devices for hybrid and organic solar cells. The field is now dominated by perovskite solar cells but also other hybrid technologies, as organic solar cells, quantum dot solar cells, and dye-sensitized solar cells and their integration into devices for photoelectrochemical solar fuel production.
Asia-Pacific International Conference on Perovskite, Organic Photovoltaics and Optoelectronics
The main topics of the Asia-Pacific International Conference on Perovskite, Organic Photovoltaics and Optoelectronics (IPEROP) are discussed every year in Asia-Pacific for gathering the recent advances in the fields of material preparation, modeling and fabrication of perovskite and hybrid and organic materials. Photovoltaic devices are analyzed from fundamental physics and materials properties to a broad set of applications. The conference also covers the developments of perovskite optoelectronics, including light-emitting diodes, lasers, optical devices, nanophotonics, nonlinear optical properties, colloidal nanostructures, photophysics and light-matter coupling.
The International Conference on Perovskite Thin Film Photovoltaics Perovskite Photonics and Optoelectronics (NIPHO) is the best place to hear the latest developments in perovskite solar cells as well as on recent advances in the fields of perovskite light-emitting diodes, lasers, optical devices, nanophotonics, nonlinear optical properties, colloidal nanostructures, photophysics and light-matter coupling.