The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

Sample complexity results from computational learning theory, when applied to neural network learning for pattern classification problems, suggest that for good generalization performance the number of training examples should grow at least linearly with the number of adjustable parameters in the network. Results in this paper show that if a large neural network is used for a pattern classification problem and the learning algorithm finds a network with small weights that has small squared error on the training patterns, then the generalization performance depends on the size of the weights rather than the number of weights. For example, consider a two-layer feedforward network of sigmoid units, in which the sum of the magnitudes of the weights associated with each unit is bounded by A and the input dimension is n. We show that the misclassification probability is no more than a certain error estimate (that is related to squared error on the training set) plus A3 √((log n)/m) (ignoring log A and log m factors), where m is the number of training patterns. This may explain the generalization performance of neural networks, particularly when the number of training examples is considerably smaller than the number of weights. It also supports heuristics (such as weight decay and early stopping) that attempt to keep the weights small during training. The proof techniques appear to be useful for the analysis of other pattern classifiers: when the input domain is a totally bounded metric space, we use the same approach to give upper bounds on misclassification probability for classifiers with decision boundaries that are far from the training examples.

Exponentiated gradient algorithms for conditional random fields and max-margin Markov Networks

Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore an important problem, and becomes a key factor when learning from very large data sets. This paper describes exponentiated gradient (EG) algorithms for training such models, where EG updates are applied to the convex dual of either the log-linear or max-margin objective function; the dual in both the log-linear and max-margin cases corresponds to minimizing a convex function with simplex constraints. We study both batch and online variants of the algorithm, and provide rates of convergence for both cases. In the max-margin case, O(1/ε) EG updates are required to reach a given accuracy ε in the dual; in contrast, for log-linear models only O(log(1/ε)) updates are required. For both the max-margin and log-linear cases, our bounds suggest that the online EG algorithm requires a factor of n less computation to reach a desired accuracy than the batch EG algorithm, where n is the number of training examples. Our experiments confirm that the online algorithms are much faster than the batch algorithms in practice. We describe how the EG updates factor in a convenient way for structured prediction problems, allowing the algorithms to be efficiently applied to problems such as sequence learning or natural language parsing. We perform extensive evaluation of the algorithms, comparing them to L-BFGS and stochastic gradient descent for log-linear models, and to SVM-Struct for max-margin models. The algorithms are applied to a multi-class problem as well as to a more complex large-scale parsing task. In all these settings, the EG algorithms presented here outperform the other methods.

Stochastic models for regulatory networks of the genetic toggle switch

Bistability arises within a wide range of biological systems from the λ phage switch in bacteria to cellular signal transduction pathways in mammalian cells. Changes in regulatory mechanisms may result in genetic switching in a bistable system. Recently, more and more experimental evidence in the form of bimodal population distributions indicates that noise plays a very important role in the switching of bistable systems. Although deterministic models have been used for studying the existence of bistability properties under various system conditions, these models cannot realize cell-to-cell fluctuations in genetic switching. However, there is a lag in the development of stochastic models for studying the impact of noise in bistable systems because of the lack of detailed knowledge of biochemical reactions, kinetic rates, and molecular numbers. In this work, we develop a previously undescribed general technique for developing quantitative stochastic models for large-scale genetic regulatory networks by introducing Poisson random variables into deterministic models described by ordinary differential equations. Two stochastic models have been proposed for the genetic toggle switch interfaced with either the SOS signaling pathway or a quorum-sensing signaling pathway, and we have successfully realized experimental results showing bimodal population distributions. Because the introduced stochastic models are based on widely used ordinary differential equation models, the success of this work suggests that this approach is a very promising one for studying noise in large-scale genetic regulatory networks.

Computational approaches for modelling intrinsic noise and delays in genetic regulatory networks

This chapter focuses on the interactions and roles between delays and intrinsic noise effects within cellular pathways and regulatory networks. We address these aspects by focusing on genetic regulatory networks that share a common network motif, namely the negative feedback loop, leading to oscillatory gene expression and protein levels. In this context, we discuss computational simulation algorithms for addressing the interplay of delays and noise within the signaling pathways based on biological data. We address implementational issues associated with efficiency and robustness. In a molecular biology setting we present two case studies of temporal models for the Hes1 gene (Monk, 2003; Hirata et al., 2002), known to act as a molecular clock, and the Her1/Her7 regulatory system controlling the periodic somite segmentation in vertebrate embryos (Giudicelli and Lewis, 2004; Horikawa et al., 2006).

Emergent task-specific object semantics through distributed experience networks

Autonomous development of sensorimotor coordination enables a robot to adapt and change its action choices to interact with the world throughout its lifetime. The Experience Network is a structure that rapidly learns coordination between visual and haptic inputs and motor action. This paper presents methods which handle the high dimensionality of the network state-space which occurs due to the simultaneous detection of multiple sensory features. The methods provide no significant increase in the complexity of the underlying representations and also allow emergent, task-specific, semantic information to inform action selection. Experimental results show rapid learning in a real robot, beginning with no sensorimotor mappings, to a mobile robot capable of wall avoidance and target acquisition.

Evolving noisy oscillatory dynamics in genetic regulatory networks

We introduce a genetic programming (GP) approach for evolving genetic networks that demonstrate desired dynamics when simulated as a discrete stochastic process. Our representation of genetic networks is based on a biochemical reaction model including key elements such as transcription, translation and post-translational modifications. The stochastic, reaction-based GP system is similar but not identical with algorithmic chemistries. We evolved genetic networks with noisy oscillatory dynamics. The results show the practicality of evolving particular dynamics in gene regulatory networks when modelled with intrinsic noise.

Aerial image analysis using spiking neural networks with application to power line corridor monitoring

Trees, shrubs and other vegetation are of continued importance to the environment and our daily life. They provide shade around our roads and houses, offer a habitat for birds and wildlife, and absorb air pollutants. However, vegetation touching power lines is a risk to public safety and the environment, and one of the main causes of power supply problems. Vegetation management, which includes tree trimming and vegetation control, is a significant cost component of the maintenance of electrical infrastructure. For example, Ergon Energy, the Australia’s largest geographic footprint energy distributor, currently spends over $80 million a year inspecting and managing vegetation that encroach on power line assets. Currently, most vegetation management programs for distribution systems are calendar-based ground patrol. However, calendar-based inspection by linesman is labour-intensive, time consuming and expensive. It also results in some zones being trimmed more frequently than needed and others not cut often enough. Moreover, it’s seldom practicable to measure all the plants around power line corridors by field methods. Remote sensing data captured from airborne sensors has great potential in assisting vegetation management in power line corridors. This thesis presented a comprehensive study on using spiking neural networks in a specific image analysis application: power line corridor monitoring. Theoretically, the thesis focuses on a biologically inspired spiking cortical model: pulse coupled neural network (PCNN). The original PCNN model was simplified in order to better analyze the pulse dynamics and control the performance. Some new and effective algorithms were developed based on the proposed spiking cortical model for object detection, image segmentation and invariant feature extraction. The developed algorithms were evaluated in a number of experiments using real image data collected from our flight trails. The experimental results demonstrated the effectiveness and advantages of spiking neural networks in image processing tasks. Operationally, the knowledge gained from this research project offers a good reference to our industry partner (i.e. Ergon Energy) and other energy utilities who wants to improve their vegetation management activities. The novel approaches described in this thesis showed the potential of using the cutting edge sensor technologies and intelligent computing techniques in improve power line corridor monitoring. The lessons learnt from this project are also expected to increase the confidence of energy companies to move from traditional vegetation management strategy to a more automated, accurate and cost-effective solution using aerial remote sensing techniques.