← Back to all news
arXiv Machine Learning By Shuang Gao, Peter E. Caines

Transmission Neural Networks: Inhibitory and Excitatory Connections

Read the original on arXiv Machine Learning →

The paper extends the Transmission Neural Network model to include inhibitory connections and neurotransmitter populations. It characterizes neuron firing probabilities under technical assumptions and shows that these can be represented by a neural network with continuous two‑dimensional neuron states. The authors also derive a limit network model as the number of neurotransmitters at all synaptic connections tends to infinity and provide sufficient conditions for its stability and contraction properties.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 18

A concentration result for multilayer feedforward neural networks

arXiv:2608. 15335v1 Announce Type: new Abstract: We consider for an arbitrary fixed $\rho$ and for each positive integer $n$ a multilayer feedforward artificial neural network with $\rho$ layers, $n$ neurons in the first layer (the input layer) and only one neuron, the output neuron, in the last layer.

By Vera Koponen
More like this →
arXiv AI
Sep 16

Equivalence of approximation by networks of single- and multi-spike neurons

The paper demonstrates that for a broad class of spiking neuron models, including the leaky integrate‑and‑fire with subtractive reset, any approximation bound proven for multi‑spike networks can be translated to an equivalent single‑spike network with only a linear change in neuron count, and vice versa. This establishes that single‑spike and multi‑spike neural networks possess identical approximation capabilities for general machine learning tasks. Consequently, existing approximation results for single‑spike networks automatically extend to the multi‑spike case.

By Dominik Dold, Philipp Christian Petersen
More like this →
arXiv AI
Jun 2

Updating the standard neuron model in artificial neural networks

arXiv:2605. 30370v2 Announce Type: replace-cross Abstract: From their inception in the 1950s, artificial neural networks (ANNs) started using the so-called point neuron model then prevalent in neuroscience, hoping that this analogy would allow for a better emulation of brain function.

By Raul Mohedano, Thomas Batard, Erik Velasco-Salido, Ramsses De Los Santos Mendoza, Jorge H. Mart\'inez, Stacey Levine, Marcelo Bertalm\'io
More like this →