$NRN neuron

Latest papers

1. Activation-Flexible ANN-to-SNN Conversion with Finite-State Markov Neurons cs.NE · 24 Sep · 5 hits

   …conversion methods rely on a specific correspondence between the source activation and the spiking neuron dynamics. We propose a finite-state continuous-time Markov chain (CTMC) neuron framework whose…

2. A Spiking Neural Network Model of Elementary Self-Consciousness via Endogenous Default Mode Network Dynamics q-bio.NC · 24 Sep · 3 hits

   …neuroscience. In this work, we propose a large-scale computational model incorporating a 10,000-neuron spiking neural network (SNN) based on Izhikevich dynamics. The network is structured into two…

3. Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons cs.AI · 24 Sep · 8 hits

   …for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and causally influence behaviors such as factuality recall, safety alignment, and…

4. Boolean threshold functions, neuron capacity, and memory retrieval math.PR · 24 Sep · 3 hits

   How much information can a single neuron remember? How many memories can neural networks retrieve without creating false memories? These…

5. Grammatical "grandmother neurons" are rare in LLMs cs.CL · 24 Sep · 6 hits

   …limitations, we introduce a probe-free framework for localizing linguistic selectivity at the individual neuron level. Leveraging the controlled contrasts of linguistic minimal pairs, we propose a Neuron…

6. The Fly That Stopped: Mushroom-Body-Inspired Habituation as a Reward-Free Scheduling Prior for Autonomous Penetration Testing cs.CR · 24 Sep · 1 hit

   …not an isolated habituation ablation or a vulnerability-discovery gain. A complementary study on a 13,498-neuron MaleCNS-derived circuit (501,267 synaptic edges with weight at least 5) found no action selectivity…

7. Complementary Roles of Activation and Parametric Memory in Few-Shot Learning cs.CL · 23 Sep · 3 hits

   …show that the composite task, Conditional Arithmetic, requires the synergy of both memory types. Through neuron-level analysis, we find that the model activates distinct sets of neurons when accessing the same…

8. TNLearn: An Open Source Python Package for Task-based Neurons cs.LG · 23 Sep · 8 hits

   The brain does not rely on a single type of neuron to perform all kinds of tasks; instead, it designs different neurons for different tasks. The concept…