The evolution of learning systems:to Bayes or not to be

Bayesian algorithms pose a limit to the performance learning algorithms can achieve. Natural selection should guide the evolution of information processing systems towards those limits. What can we learn from this evolution and what properties do the intermediate stages have? While this question is too general to permit any answer, progress can be made by restricting the class of information processing systems under study. We present analytical and numerical results for the evolution of on-line algorithms for learning from examples for neural network classifiers, which might include or not a hidden layer. The analytical results are obtained by solving a variational problem to determine the learning algorithm that leads to maximum generalization ability. Simulations using evolutionary programming, for programs that implement learning algorithms, confirm and expand the results. The principal result is not just that the evolution is towards a Bayesian limit. Indeed it is essentially reached. In addition we find that evolution is driven by the discovery of useful structures or combinations of variables and operators. In different runs the temporal order of the discovery of such combinations is unique. The main result is that combinations that signal the surprise brought by an example arise always before combinations that serve to gauge the performance of the learning algorithm. This latter structures can be used to implement annealing schedules. The temporal ordering can be understood analytically as well by doing the functional optimization in restricted functional spaces. We also show that there is data suggesting that the appearance of these traits also follows the same temporal ordering in biological systems. © 2006 American Institute of Physics.

A simulation analysis of spoke-terminals operating in LTL Hub-and-Spoke freight distribution systems

DUE TO COPYRIGHT RESTRICTIONS ONLY AVAILABLE FOR CONSULTATION AT ASTON UNIVERSITY LIBRARY AND INFORMATION SERVICES WITH PRIOR ARRANGEMENT The research presented in this thesis is concerned with Discrete-Event Simulation (DES) modelling as a method to facilitate logistical policy development within the UK Less-than-Truckload (LTL) freight distribution sector which has been typified by “Pallet Networks” operating on a hub-and-spoke philosophy. Current literature relating to LTL hub-and-spoke and cross-dock freight distribution systems traditionally examines a variety of network and hub design configurations. Each is consistent with classical notions of creating process efficiency, improving productivity, reducing costs and generally creating economies of scale through notions of bulk optimisation. Whilst there is a growing abundance of papers discussing both the network design and hub operational components mentioned above, there is a shortcoming in the overall analysis when it comes to discussing the “spoke-terminal” of hub-and-spoke freight distribution systems and their capabilities for handling the diverse and discrete customer profiles of freight that multi-user LTL hub-and-spoke networks typically handle over the “last-mile” of the delivery, in particular, a mix of retail and non-retail customers. A simulation study is undertaken to investigate the impact on operational performance when the current combined spoke-terminal delivery tours are separated by ‘profile-type’ (i.e. retail or nonretail). The results indicate that a potential improvement in delivery performance can be made by separating retail and non-retail delivery runs at the spoke-terminal and that dedicated retail and non-retail delivery tours could be adopted in order to improve customer delivery requirements and adapt hub-deployed policies. The study also leverages key operator experiences to highlight the main practical implementation challenges when integrating the observed simulation results into the real-world. The study concludes that DES be harnessed as an enabling device to develop a ‘guide policy’. This policy needs to be flexible and should be applied in stages, taking into account the growing retail-exposure.

Experimental validation of a predictive pyrolysis model in AspenPlus®

A novel simulation model for pyrolysis processes oflignocellulosicbiomassin AspenPlus (R) was presented at the BC&E 2013. Based on kinetic reaction mechanisms, the simulation calculates product compositions and yields depending on reactor conditions (temperature, residence time, flue gas flow rate) and feedstock composition (biochemical composition, atomic composition, ash and alkali metal content). The simulation model was found to show good correlation with existing publications. In order to further verify the model, own pyrolysis experiments in a 1 kg/h continuously fed fluidized bed fast pyrolysis reactor are performed. Two types of biomass with different characteristics are processed in order to evaluate the influence of the feedstock composition on the yields of the pyrolysis products and their composition. One wood and one straw-like feedstock are used due to their different characteristics. Furthermore, the temperature response of yields and product compositions is evaluated by varying the reactor temperature between 450 and 550 degrees C for one of the feedstocks. The yields of the pyrolysis products (gas, oil, char) are determined and their detailed composition is analysed. The experimental runs are reproduced with the corresponding reactor conditions in the AspenPlus model and the results compared with the experimental findings.

Prevalence and audiological features in carriers of GJB2 mutations, c.35delG and c.101T>C (p.M34T), in a UK population study

OBJECTIVES: To determine the carrier rate of the GJB2 mutation c.35delG and c.101T>C in a UK population study; to determine whether carriers of the mutation had worse hearing or otoacoustic emissions compared to non-carriers. DESIGN: Prospective cohort study. SETTING: University of Bristol, UK. PARTICIPANTS: Children in the Avon Longitudinal Study of Parents and Children. 9202 were successfully genotyped for the c.35delG mutation and c.101>T and classified as either carriers or non-carriers. OUTCOME MEASURES: Hearing thresholds at age 7, 9 and 11 years and otoacoustic emissions at age 9 and 11. RESULTS: The carrier frequency of the c.35delG mutation was 1.36% (95% CI 1.13 to 1.62) and c.101T>C was 2.69% (95% CI 2.37 to 3.05). Carriers of c.35delG and c.101T>C had worse hearing than non-carriers at the extra-high frequency of 16 kHz. The mean difference in hearing at age 7 for the c.35delG mutation was 8.53 dB (95% CI 2.99, 14.07) and 12.57 dB at age 9 (95% CI 8.10, 17.04). The mean difference for c.101T>C at age 7 was 3.25 dB (95% CI -0.25 to 6.75) and 7.61 dB (95% CI 4.26 to 10.96) at age 9. Otoacoustic emissions were smaller in the c.35delG mutation carrier group: at 4 kHz the mean difference was -4.95 dB (95% CI -6.70 to -3.21) at age 9 and -3.94 dB (95% CI -5.78 to -2.10) at age 11. There was weak evidence for differences in otoacoustic emissions amplitude for c.101T>C carriers. CONCLUSION: Carriers of the c.35delG mutation and c.101T>C have worse extra-high-frequency hearing than non-carriers. This may be a predictor for changes in lower-frequency hearing in adulthood. The milder effects observed in carriers of c.101T>C are in keeping with its classification as a mutation causing mild/moderate hearing loss in homozygosity or compound heterozygosity.