The mammalian brain is the most capable and complex computing entity known today, and for years there has been research focused on reproducing the brain's capabilities. An early example of this endeavor was the perceptron which has become a core building block of neural network models in the deep learning era. Despite many successes achieved through deep learning, these networks behave much differently than their biological counterparts. In a search for improvements to things like training time and dataset size, power consumption, noise, and adversarial input tolerance, research is looking towards the brain, and bio-inspired computing models. Spiking neural networks (SNNs) take a step closer to biology in their operation and are the focus of much research, geared towards reproducing some of these novel features of the brain. As of yet, SNNs have not reached their full potential. This work explores the advancement of SNNs though introduction of a novel astrocyte model. Astrocytes, initially thought to be passive support cells in the brain are now known to actively participate in neural processing. The proposed astrocyte model is geared towards synaptic plasticity and is shown to generalize and extend spike-timing dependent plasticity (STDP). In addition, the model supports plasticity-focused multi-synapse integration. Logical AND was used as a test function for multi-synapse astrocyte plasticity, and convergence for a single leaky integrate and fire (LIF) neuron with 2, 3, and 4 synapses was demonstrated. The plasticity model is general and many other functions could presumably be used in-place of AND, taking advantage of a multi-synapse view. This leaves a solid path forward for future work.

Spiking neural networks (SNNs) have generated considerable excitement because of their computational properties, believed to be superior to conventional von Neumann machines, and sharing properties with living brains. Yet progress building these systems has been limited because we lack a design methodology. We present a gene-driven network growth algorithm that enables a genetic algorithm (evolutionary computation) to generate and test SNNs. The genome length for this algorithm grows O(n) where n is the number of neurons; n is also evolved. The genome not only specifies the network topology, but all its parameters as well. In experiments, the algorithm discovered SNNs that effectively produce a robust spike bursting behavior given tonic inputs, an application suitable for central pattern generators. Even though evolution did not include perturbations of the input spike trains, the evolved networks showed remarkable robustness to such perturbations. On a second task, a sequence detector, several related discriminating designs were found, all made “errors” in that they fired when input spikes were simultaneous (i.e. not strictly in sequence), but not when they were out of sequence. They also fired when the sequence was too close for the teacher to have declared they were in sequence. That is, evolution produced these behaviors even though it was not explicitly rewarded for doing so. We are optimistic that this technology might be scaled up to produce robust SNN designs that humans would be hard pressed to produce.

Interdisciplinary problem solving in computational biology requires a fundamental understanding of complex biological adaptive systems, from cellular to molecular level in order to tackle challenging problems such as neurodegenerative diseases. In this work we present a description and an initial evaluation of a Spiking Neural Network-Genetic Algorithm (SNN-GA) system we are developing for the computational prediction of transcription factor binding sites (TFBS). The SNN-GA approach is based on modeling information processing of biological neurons through evolutionary processes. The goal of our work is to reduce the number of false positives in the predicted TFBSs, through a more precise modeling of information contained in the alignments in the training data. We show an evaluation of four proposed network topologies that represent TFBS data. We use real TFBS data from the TRANSFAC®database and appropriately generated negative samples. We evaluated the network topologies one three well-known models for transcription factors: RSRFC4, ZID and p53. Benchmark performances for these models are given using MAPPER and MATCH™. The results show that our method has the potential to attain very high classification accuracy.

Commercial detection plays an important role in various video segmentation and indexing applications. It provides high-level program segmentation so that other algorithms can be applied on the true program material in the broadcast. It is a challenge to have robust commercial detection methodology for various platforms, content formats, and broadcast styles that are used all over the world. Wide deployment of such an algorithm not only requires the development of new algorithms but also updating and tuning of parameters for existing algorithms. We present visual commercial detectors that rely on features including, luminance, letterbox, and keyframe distance. These detectors were developed after a careful study of the various features that can be extracted during MPEG-encoding process in real time. Due to the intermittent nature of the features, and platform restrictions, the commercial detection relies on a set of thresholds to keep the implementation as simple as possible. We evolved these thresholds using genetic algorithms (GAs) to optimize the performance. We show how a scalar genetic algorithm can locate sets of parameters in a multi-objective space (precision and recall) that outperform the values selected by an expert engineer. We present the results of optimizing a commercial detection algorithm for different data sets and parameter sets. In this paper we show that GAs drastically improved our approach and enabled fast prototyping and performance tuning of commercial detection algorithms.

This article describes ongoing research on content sensitive recombination operators for genetic algorithms. A motivation behind this line of inquiry stems from the observation that biological chromosomes appear to contain special nucleotide sequences whose job is to influence the recombination of the expressible genes. We think of these as punctuation marks telling the recombination operators how to do their job. Furthermore, we assume that the distribution of these marks (part of the representation) in a gene pool is determined by the same survival-of-the-fittest and genetic recombination mechanisms that account for the distribution of the expressible genes (the knowledge). A goal of this project is to devise such mechanisms for genetic algorithms and thereby to link the adaptation of a representation to the adaptation of its contents. We hope to do so in a way that capitalizes on the intrinsically parallel behavior of the traditional genetic algorithm. We anticipate benefits of this for machine learning. We describe one mechanism we have devised and present some empirical evidence that suggests it may be as good as or better than a traditional genetic algorithm across a range of search problems. We attempt to show that its action does successfully adapt the search mechanics to the problem space and provide the beginnings of a theory to explain its good perfomance.