Genetic and bacterial programming for B-Spline neural networks design

The design phase of B-spline neural networks is a highly computationally complex task. Existent heuristics have been found to be highly dependent on the initial conditions employed. Increasing interest in biologically inspired learning algorithms for control techniques such as Artificial Neural Networks and Fuzzy Systems is in progress. In this paper, the Bacterial Programming approach is presented, which is based on the replication of the microbial evolution phenomenon. This technique produces an efficient topology search, obtaining additionally more consistent solutions.

Design of B-spline neural networks using a bacterial programming approach

The design phase of B-spline neural networks represents a very high computational task. For this purpose, heuristics have been developed, but have been shown to be dependent on the initial conditions employed. In this paper a new technique, Bacterial Programming, is proposed, whose principles are based on the replication of the microbial evolution phenomenon. The performance of this approach is illustrated and compared with existing alternatives.

A hybrid training method for B-spline neural networks

Current and past research has brought up new views related to the optimization of neural networks. For a fixed structure, second order methods are seen as the most promising. From previous works we have shown how second order methods are of easy applicability to a neural network. Namely, we have proved how the Levenberg-Marquard possesses not only better convergence but how it can assure the convergence to a local minima. However, as any gradient-based method, the results obtained depend on the startup point. In this work, a reformulated Evolutionary algorithm - the Bacterial Programming for Levenberg-Marquardt is proposed, as an heuristic which can be used to determine the most suitable starting points, therefore achieving, in most cases, the global optimum.

Training neuro-fuzzy models using evolution based algorithms

The normal design process for neural networks or fuzzy systems involve two different phases: the determination of the best topology, which can be seen as a system identification problem, and the determination of its parameters, which can be envisaged as a parameter estimation problem. This latter issue, the determination of the model parameters (linear weights and interior knots) is the simplest task and is usually solved using gradient or hybrid schemes. The former issue, the topology determination, is an extremely complex task, especially if dealing with real-world problems.

Design of neuro-fuzzy models by evolutionary and gradient-based algorithms

All systems found in nature exhibit, with different degrees, a nonlinear behavior. To emulate this behavior, classical systems identification techniques use, typically, linear models, for mathematical simplicity. Models inspired by biological principles (artificial neural networks) and linguistically motivated (fuzzy systems), due to their universal approximation property, are becoming alternatives to classical mathematical models. In systems identification, the design of this type of models is an iterative process, requiring, among other steps, the need to identify the model structure, as well as the estimation of the model parameters. This thesis addresses the applicability of gradient-basis algorithms for the parameter estimation phase, and the use of evolutionary algorithms for model structure selection, for the design of neuro-fuzzy systems, i.e., models that offer the transparency property found in fuzzy systems, but use, for their design, algorithms introduced in the context of neural networks. A new methodology, based on the minimization of the integral of the error, and exploiting the parameter separability property typically found in neuro-fuzzy systems, is proposed for parameter estimation. A recent evolutionary technique (bacterial algorithms), based on the natural phenomenon of microbial evolution, is combined with genetic programming, and the resulting algorithm, bacterial programming, advocated for structure determination. Different versions of this evolutionary technique are combined with gradient-based algorithms, solving problems found in fuzzy and neuro-fuzzy design, namely incorporation of a-priori knowledge, gradient algorithms initialization and model complexity reduction.

Programming rumen bacterial communities in newborn Merino lambs

Establishment of the rumen microbiome can be affected by both early-life dietary measures and rumen microbial inoculation. This study used a 2 × 3 factorial design to evaluate the effects of inclusion of dietary fat type and the effects of rumen inoculum from different sources on ruminal bacterial communities present in early stages of the lambs’ life. Two different diets were fed ad libitum to 36 pregnant ewes (and their lambs) from 1 month pre-lambing until weaning. Diets consisted of chaffed lucerne and cereal hay and 4% molasses, with either 4% distilled coconut oil (CO) provided as a source of rumen-active fat or 4% Megalac® provided as a source of rumen-protected fat (PF). One of three inoculums was introduced orally to all lambs, being either (1) rumen fluid from donor ewes fed the PF diet; (2) rumen fluid from donor ewes fed CO; or (3) a control treatment of MilliQ-water. After weaning at 3 months of age, each of the six lamb treatment groups were grazed in spatially separated paddocks. Rumen bacterial populations of ewes and lambs were characterised using 454 amplicon pyrosequencing of the V3/V4 regions of the 16S rRNA gene. Species richness and biodiversity of the bacterial communities were found to be affected by the diet in ewes and lambs and by inoculation treatment of the lambs. Principal coordinate analysis and analysis of similarity (ANOSIM) showed between diet differences in bacterial community groups existed in ewes and differential bacterial clusters occurred in lambs due to both diet and neonatal inoculation. Diet and rumen inoculation acted together to clearly differentiate the bacterial communities through to weaning, however the microbiome effects of these initial early life interventions diminished with time so that rumen bacterial communities showed greater similarity 2 months after weaning. These results demonstrate that ruminal bacterial communities of newborn lambs can be altered by modifying the diet of their mothers. Moreover, the rumen microbiome of lambs can be changed by diet while they are suckling or by inoculating their rumen, and resulting changes in the rumen bacterial microbiome can persist beyond weaning.

Genetic programming and bacterial algorithm for neural networks and fuzzy systems design

In the field of control systems it is common to use techniques based on model adaptation to carry out control for plants for which mathematical analysis may be intricate. Increasing interest in biologically inspired learning algorithms for control techniques such as Artificial Neural Networks and Fuzzy Systems is in progress. In this line, this paper gives a perspective on the quality of results given by two different biologically connected learning algorithms for the design of B-spline neural networks (BNN) and fuzzy systems (FS). One approach used is the Genetic Programming (GP) for BNN design and the other is the Bacterial Evolutionary Algorithm (BEA) applied for fuzzy rule extraction. Also, the facility to incorporate a multi-objective approach to the GP algorithm is outlined, enabling the designer to obtain models more adequate for their intended use.

Programming stress-induced altruistic death in engineered bacteria.

Programmed death is often associated with a bacterial stress response. This behavior appears paradoxical, as it offers no benefit to the individual. This paradox can be explained if the death is 'altruistic': the killing of some cells can benefit the survivors through release of 'public goods'. However, the conditions where bacterial programmed death becomes advantageous have not been unambiguously demonstrated experimentally. Here, we determined such conditions by engineering tunable, stress-induced altruistic death in the bacterium Escherichia coli. Using a mathematical model, we predicted the existence of an optimal programmed death rate that maximizes population growth under stress. We further predicted that altruistic death could generate the 'Eagle effect', a counter-intuitive phenomenon where bacteria appear to grow better when treated with higher antibiotic concentrations. In support of these modeling insights, we experimentally demonstrated both the optimality in programmed death rate and the Eagle effect using our engineered system. Our findings fill a critical conceptual gap in the analysis of the evolution of bacterial programmed death, and have implications for a design of antibiotic treatment.

A role of cellular prion protein in programming T-cell cytokine responses in disease.

The cellular prion protein (PrPC) is widely expressed in neural and non-neural tissues, but its function is unknown. Elucidation of the part played by PrPC in adaptive immunity has been a particular conundrum: increased expression of cell surface PrPC has been documented during T-cell activation, yet the functional significance of this activation remains unclear, with conflicting data on the effects of Prnp gene knockout on various parameters of T-cell immunity. We show here that Prnp mRNA is highly inducible within 8–24 h of T-cell activation, with surface protein levels rising from 24 h. When measured in parallel with CD69 and CD25, PrPC is a late activation antigen. Consistent with its up-regulation being a late activation event, PrP deletion did not alter T-cell-antigen presenting cell conjugate formation. Most important, activated PrP0/0 T cells demonstrated much reduced induction of several T helper (Th) 1, Th2, and Th17 cytokines, whereas others, such as TNF- and IL-9, were unaffected. These changes were investigated in the context of an autoimmune model and a bacterial challenge model. In experimental autoimmune encephalomyelitis, PrP-knockout mice showed enhanced disease in the face of reduced IL-17 responses. In a streptococcal sepsis model, this constrained cytokine program was associated with poorer local control of infection, although with reduced bacteremia. The findings indicate that PrPC is a potentially important molecule influencing T-cell activation and effector function.

Automated Feedback for 'Fill in the Gap' Programming Exercises

Timely feedback is a vital component in the learning process. It is especially important for beginner students in Information Technology since many have not yet formed an effective internal model of a computer that they can use to construct viable knowledge. Research has shown that learning efficiency is increased if immediate feedback is provided for students. Automatic analysis of student programs has the potential to provide immediate feedback for students and to assist teaching staff in the marking process. This paper describes a “fill in the gap” programming analysis framework which tests students’ solutions and gives feedback on their correctness, detects logic errors and provides hints on how to fix these errors. Currently, the framework is being used with the Environment for Learning to Programming (ELP) system at Queensland University of Technology (QUT); however, the framework can be integrated into any existing online learning environment or programming Integrated Development Environment (IDE)

Losing their marbles : syntax-free programming for assessing problem-solving skills

Novice programmers have difficulty developing an algorithmic solution while simultaneously obeying the syntactic constraints of the target programming language. To see how students fare in algorithmic problem solving when not burdened by syntax, we conducted an experiment in which a large class of beginning programmers were required to write a solution to a computational problem in structured English, as if instructing a child, without reference to program code at all. The students produced an unexpectedly wide range of correct, and attempted, solutions, some of which had not occurred to their teachers. We also found that many common programming errors were evident in the natural language algorithms, including failure to ensure loop termination, hardwiring of solutions, failure to properly initialise the computation, and use of unnecessary temporary variables, suggesting that these mistakes are caused by inexperience at thinking algorithmically, rather than difficulties in expressing solutions as program code.