Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods that are used in the literature and in industry. This paper describes a set of concrete best practices that document analysis researchers can use to get good results with neural networks. The most important practice is getting a training set as large as possible: we expand the training set by adding a new form of distorted data. The next most important practice is that convolutional neural networks are better suited for visual document tasks than fully connected networks. We propose that a simple "do-it-yourself" implementation of convolution with a flexible architecture is suitable for many visual document problems. This simple convolutional neural network does not require complex methods, such as momentum, weight decay, structuredependent learning rates, averaging layers, tangent prop, or even finely-tuning the architecture. The end result is a very simple yet general architecture which can yield state-of-the-art performance for document analysis. We illustrate our claims on the MNIST set of English digit images.

Invertebrate pathogens and their hosts are taxonomically diverse. Despite this, there is one unifying concept relevant to all such parasitic associations: Both pathogen and host adapt to maximize their own reproductive output and ultimate fitness. The strategies adopted by pathogens and hosts to achieve this goal are almost as diverse as the organisms themselves, but studies examining such relationships have traditionally concentrated only on aspects of host physiology. Here we review examples of host-altered behavior and consider these within a broad ecological and evolutionary context. Research on pathogen-induced and host-mediated behavioral changes demonstrates the range of altered behaviors exhibited by invertebrates including behaviorally induced fever, elevation seeking, reduced or increased activity, reduced response to semiochemicals, and changes in reproductive behavior. These interactions are sometimes quite bizarre, intricate, and of great scientific interest.

This chapter describes ecological case histories for a number of species belonging to order Entomophthorales (Massospora spp., Neozygites spp., Strongwellsea castrans, Entomophthora muscae, Entomophaga grylli, Entomophthora thripidum and Conidiobolus spp.) and discusses the life cycle, taxonomy, spatial and temporal distribution, persistence, dispersal and impact of these species on host biology and behaviour which are keys to the effective exploitation in specific environments. The use of these species in pest management is discussed with particular emphasis on future opportunities.

No abstract

No abstract