IMPROBED: Multiple Problem-Solving Brain via Evolved Developmental Programs.

Artificial neural networks (ANNs) were originally inspired by the brain; however, very few models use evolution and development, both of which are fundamental to the construction of the brain. We describe a simple neural model, called IMPROBED, in which two neural programs construct an artificial brain that can simultaneously solve multiple computational problems. One program represents the neuron soma and the other the dendrite. The soma program decides whether neurons move, change, die, or replicate. The dendrite program decides whether dendrites extend, change, die, or replicate. Since developmental programs build networks that change over time, it is necessary to define new problem classes that are suitable to evaluate such approaches. We show that the pair of evolved programs can build a single network from which multiple conventional ANNs can be extracted, each of which can solve a different computational problem. Our approach is quite general and it could be applied to a much wider variety of problems.

High throughput software-based gradient tree boosting positioning for PET systems.

The supervised machine learning technique Gradient Tree Boosting (GTB) has shown good accuracy for position estimation of gamma interaction in PET crystals for bench-top experiments while its computational requirements can easily be adjusted. Transitioning to preclinical and clinical applications requires near real-time processing in the scale of full PET systems. In this work, a high throughput GTB-based singles positioning C++ implementation is proposed and a series of optimizations are evaluated regarding their effect on the achievable processing throughput. Moreover, the crucial feature and parameter selection for GTB is investigated for the segmented detectors of the Hyperion IIDPET insert with two main models and a range of GTB hyperparameters. The proposed framework achieves singles positioning throughputs of more than 9.5 GB/s for smaller models and of 240 MB/s for more complex models on a recent Intel Skylake server. Detailed throughput analysis reveals the key performance limiting factors, and an empirical throughput model is derived to guide the GTB model selection process and scanner design decisions. The throughput model allows for throughput estimations with a mean absolute error (MAE) of 175.78 MB/s.

A substrate-independent framework to characterize reservoir computers.

The reservoir computing (RC) framework states that any nonlinear, input-driven dynamical system (the reservoir) exhibiting properties such as a fading memory and input separability can be trained to perform computational tasks. This broad inclusion of systems has led to many new physical substrates for RC. Properties essential for reservoirs to compute are tuned through reconfiguration of the substrate, such as change in virtual topology or physical morphology. As a result, each substrate possesses a unique 'quality'-obtained through reconfiguration-to realize different reservoirs for different tasks. Here we describe an experimental framework to characterize the quality of potentially any substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can help map the non-trivial relationship between properties and task performance. In the wider context, the framework offers a greater understanding as to what makes a dynamical system compute, helping improve the design of future substrates for RC.

Evolutionary Algorithms for Boolean Functions in Diverse Domains of Cryptography.

The role of Boolean functions is prominent in several areas including cryptography, sequences, and coding theory. Therefore, various methods for the construction of Boolean functions with desired properties are of direct interest. New motivations on the role of Boolean functions in cryptography with attendant new properties have emerged over the years. There are still many combinations of design criteria left unexplored and in this matter evolutionary computation can play a distinct role. This article concentrates on two scenarios for the use of Boolean functions in cryptography. The first uses Boolean functions as the source of the nonlinearity in filter and combiner generators. Although relatively well explored using evolutionary algorithms, it still presents an interesting goal in terms of the practical sizes of Boolean functions. The second scenario appeared rather recently where the objective is to find Boolean functions that have various orders of the correlation immunity and minimal Hamming weight. In both these scenarios we see that evolutionary algorithms are able to find high-quality solutions where genetic programming performs the best.

Evolution of cartesian genetic programs for development of learning neural architecture.

Although artificial neural networks have taken their inspiration from natural neurological systems, they have largely ignored the genetic basis of neural functions. Indeed, evolutionary approaches have mainly assumed that neural learning is associated with the adjustment of synaptic weights. The goal of this paper is to use evolutionary approaches to find suitable computational functions that are analogous to natural sub-components of biological neurons and demonstrate that intelligent behavior can be produced as a result of this additional biological plausibility. Our model allows neurons, dendrites, and axon branches to grow or die so that synaptic morphology can change and affect information processing while solving a computational problem. The compartmental model of a neuron consists of a collection of seven chromosomes encoding distinct computational functions inside the neuron. Since the equivalent computational functions of neural components are very complex and in some cases unknown, we have used a form of genetic programming known as Cartesian genetic programming (CGP) to obtain these functions. We start with a small random network of soma, dendrites, and neurites that develops during problem solving by repeatedly executing the seven chromosomal programs that have been found by evolution. We have evaluated the learning potential of this system in the context of a well-known single agent learning problem, known as Wumpus World. We also examined the harder problem of learning in a competitive environment for two antagonistic agents, in which both agents are controlled by independent CGP computational networks (CGPCN). Our results show that the agents exhibit interesting learning capabilities.

An evolutionary system using development and artificial Genetic Regulatory Networks for electronic circuit design.

Biology presents incomparable, but desirable, characteristics compared to engineered systems. Inspired by biological development, we have devised a multi-layered design architecture that attempts to capture the favourable characteristics of biological mechanisms for application to design problems. We have identified and implemented essential features of Genetic Regulatory Networks (GRNs) and cell signalling which lead to self-organization and cell differentiation. We have applied this to electronic circuit design.

Through the interaction of neutral and adaptive mutations, evolutionary search finds a way.

An evolutionary system that supports the interaction of neutral and adaptive mutations is investigated. Experimental results on a Boolean function and needle-in-haystack problems show that this system enables evolutionary search to find better solutions faster. Through a novel analysis based on the ratio of neutral to adaptive mutations, we identify this interaction as an engine that automatically adjusts the relative amounts of exploration and exploitation to achieve effective search (i.e., it is self-adaptive). Moreover, a hypothesis to describe the search process in this system is proposed and investigated. Our findings lead us to counter the arguments of those who dismiss the usefulness of neutrality. We argue that the benefits of neutrality are intimately related to its implementation, so that one must be cautious about making general claims about its merits or demerits.

Guidelines: From artificial evolution to computational evolution: a research agenda.

Computational scientists have developed algorithms inspired by natural evolution for at least 50 years. These algorithms solve optimization and design problems by building solutions that are 'more fit' relative to desired properties. However, the basic assumptions of this approach are outdated. We propose a research programme to develop a new field: computational evolution. This approach will produce algorithms that are based on current understanding of molecular and evolutionary biology and could solve previously unimaginable or intractable computational and biological problems.

Examination of murine tear film.

PURPOSE: To define spatially any free aqueous layer in murine tear film. METHOD: A pre-zeroed microelectrode was touched to the superficial corneal epithelium and then raised in steps of 1 micro m through the murine tear film into the air and then retraced along the same path. Other murine tear films were partially probed with a spatial resolution of 0.1 micro m. The reference microelectrode was placed in a fragment of 3% polyacrylamide gel equilibrated against 154 mM NaCl and located on the nasal quadrant of the scleral conjunctiva. Other murine corneas were quick frozen in melting isopentane and freeze substituted or pretreated with cetylpyridinium chloride and then examined by transmission electron microscopy. RESULTS: The recorded electrical profiles of the tear film were reproducible in each preparation and showed a relatively uniform positive electrical potential throughout their whole thickness, except within 0.5 micro m of the epithelial surface when the potential reversed to negative values. The thickness of mouse tear film averaged 7.4 +/- 0.8 micro m (mean +/- SD, n = 40). The electron microscope images showed the murine tear film to have a relatively uniform positive electron density throughout the thickness. CONCLUSIONS: Electrical profiles of the murine tear film presented no evidence of a separate free aqueous phase. The tear film is observed as an aqueous gel that includes anion-exchanging polyelectrolytes throughout most of its thickness, but within 0.5 micro m of the epithelial surface, it changes to cation-exchanging polyelectrolytes. Electron microscope images provide some supporting evidence.