Temporal support vectors for spiking neuronal networks

When neural circuits learn to perform a task, it is often the case that there are many sets of synaptic connections that are consistent with the task. However, only a small number of possible solutions are robust to noise in the input and are capable of generalizing their performance of the task to new inputs. Finding such good solutions is an important goal of learning systems in general and neuronal circuits in particular. For systems operating with static inputs and outputs, a well known approach to the problem is the large margin methods such as Support Vector Machines (SVM). By maximizing the distance of the data vectors from the decision surface, these solutions enjoy increased robustness to noise and enhanced generalization abilities. Furthermore, the use of the kernel method enables SVMs to perform classification tasks that require nonlinear decision surfaces. However, for dynamical systems with event based outputs, such as spiking neural networks and other continuous time threshold crossing systems, this optimality criterion is inapplicable due to the strong temporal correlations in their input and output. We introduce a novel extension of the static SVMs - The Temporal Support Vector Machine (T-SVM). The T-SVM finds a solution that maximizes a new construct - the dynamical margin. We show that T-SVM and its kernel extensions generate robust synaptic weight vectors in spiking neurons and enable their learning of tasks that require nonlinear spatial integration of synaptic inputs. We propose T-SVM with nonlinear kernels as a new model of the computational role of the nonlinearities and extensive morphologies of neuronal dendritic trees.

• Publication year

  2022

• Venue

  Unknown venue

• Publication date

  2022-05-28

• Fields of study

  Biology, Mathematics, Physics, Computer Science

• Identifiers
  arXiv 2205.14544
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Nonlinear Programming

  2021cited by this paper
• Numerical Optimization

  2018cited by this paper
• The AdaTron: An Adaptive Perceptron Algorithm

  2017cited by this paper
• An Augmented Two-Layer Model Captures Nonlinear Analog Spatial Integration Effects in Pyramidal Neuron Dendrites

  2014cited by this paper
• To spike, or when to spike?

  2014cited by this paper
• Learning precisely timed spikes.

  2014cited by this paper
• Active properties of neocortical pyramidal neuron dendrites.

  2013cited by this paper
• Multiple Incremental Decremental Learning of Support Vector Machines

  2009cited by this paper
• Incremental Support Vector Learning: Analysis, Implementation and Applications

  2006cited by this paper
• Dendritic computation.

  2005cited by this paper
• Computational subunits in thin dendrites of pyramidal cells

  2004cited by this paper
• Impact of active dendrites and structural plasticity on the memory capacity of neural tissue.

  2001cited by this paper
• Numerical Optimization (Springer Series in Operations Research and Financial Engineering)

  2000cited by this paper
• The Nature of Statistical Learning Theory

  2000cited by this paper
• Chaotic Balanced State in a Model of Cortical Circuits

  1998cited by this paper
• Chaos in Neuronal Networks with Balanced Excitatory and Inhibitory Activity

  1996cited by this paper
• Directionally selective complex cells and the computation of motion energy in cat visual cortex.

  1992cited by this paper
• Perceptrons: expanded edition

  1988cited by this paper
• The space of interactions in neural network models

  1988cited by this paper
• Spatiotemporal energy models for the perception of motion.

  1985cited by this paper
• PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS

  1963cited by this paper
• Systemtheoretische Analyse der Zeit-, Reihenfolgen- und Vorzeichenauswertung bei der Bewegungsperzeption des Rüsselkäfers Chlorophanus

  1956cited by this paper

• No citing papers are available for this paper.