Nowadays, computer scientists have shown the interest in the study of social insect's behaviour in neural networks area for solving different combinatorial and statistical problems. Chief among these is the Artificial Bee Colony (ABC) algorithm. This paper investigates the use of ABC algorithm that simulates the intelligent foraging behaviour of a honey bee swarm. Multilayer Perceptron (MLP) trained with the standard back propagation algorithm normally utilises computationally intensive training algorithms. One of the crucial problems with the backpropagation (BP) algorithm is that it can sometimes yield the networks with suboptimal weights because of the presence of many local optima in the solution space. To overcome ABC algorithm used in this work to train MLP learning the complex behaviour of earthquake time series data trained by BP, the performance of MLP-ABC is benchmarked against MLP training with the standard BP. The experimental result shows that MLP-ABC performance is better than MLP-BP for time series data.

Current automatic handwriting recognition algorithms are already pretty good at learning to recognize handwritten digits. More than a decade ago, Multilayer Perceptrons or MLPs (Werbos, 1974; LeCun, 1985; Rumelhart et al., 1986) were among the first classifiers tested on the now famous MNIST handwritten digit recognition benchmark. Most had few layers or few artificial neurons (units) per layer (LeCun et al., 1998), but apparently back then these were the biggest feasible MLPs, trained when CPU cores were at least 20 times slower than today. A more recent MLP with a single hidden layer of 800 units achieved 0.70% error (Simard et al., 2003). The latest substantial improvement by others occurred in 2003 (Simard et al., 2003) (error rate 0.4%).

The paper develops a connection between traditional perceptron algorithms and recently introduced herding algorithms. It is shown that both algorithms can be viewed as an application of the perceptron cycling theorem. This connection strengthens some herding results and suggests new (supervised) herding algorithms that, like CRFs or discriminative RBMs, make predictions by conditioning on the input attributes. We develop and investigate variants of conditional herding, and show that conditional herding leads to practical algorithms that perform better than or on par with related classifiers such as the voted perceptron and the discriminative RBM.

Artificial neural networks (ANNs, or simply NNs) are inspired by biological nervous systems and consist of simple processing units (artificial neurons) that are interconnected by weighted connections. Neural networks can be "trained" to solve problems that are difficult to solve by conventional computer algorithms. This paper presents the development and implementation of a generalized back-propagation multi-layer perceptron (MLP) neural network architecture described in very high speed hardware description language (VHDL). The development of hardware platforms has been complicated by the high hardware cost and quantity of the arithmetic operations required in an online MLP, i.e., one used to solve real-time problems. The challenge is thus to find an architecture that minimizes hardware costs while maximizing performance, accuracy, and parameterization. The paper describes herein a platform that offers a high degree of parameterization while maintaining performance comparable to other hardware based MLP implementations.

Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0.35% error rate on the famous MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images, and graphics cards to greatly speed up learning.

We present AROW, a new online learning algorithm that combines several properties of successful : large margin training, confidence weighting, and the capacity to handle non-separable data. AROW performs adaptive regularization of the prediction function upon seeing each new instance, allowing it to perform especially well in the presence of label noise. We derive a mistake bound, similar in form to the second order perceptron bound, which does not assume separability. We also relate our algorithm to recent confidence-weighted online learning techniques and empirically show that AROW achieves state-of-the-art performance and notable robustness in the case of non-separable data.

We propose a perceptron-style algorithm for fast discriminative training of structured latent variable model. This method extends the perceptron algorithm for the learning with latent dependencies, as an alternative to existing probabilistic latent variable models. It relies on Viterbi decoding over latent variables, combined with simple additive updates. Its training cost is significantly lower than that of probabilistic latent variable models, while it gives comparable or even superior classification accuracy on our tasks. Experiments on natural language processing problems demonstrate that its results are among those good reports on corresponding data sets.

In this paper, we present an application of neural networks in the renewable energy domain. We have developed a methodology for the daily prediction of global solar radiation on a horizontal surface. We use an ad-hoc time series preprocessing and a Multi-Layer Perceptron (MLP) in order to predict solar radiation at daily horizon. First results are promising with nRMSE < 21% and RMSE < 998 Wh/m2. Our optimized MLP presents prediction similar to or even better than conventional methods such as ARIMA techniques, Bayesian inference, Markov chains and k-Nearest-Neighbors approximators. Moreover we found that our data preprocessing approach can reduce significantly forecasting errors.

A new algorithm for on-line learning linear-threshold functions is proposed which efficiently combines second-order statistics about the data with the logarithmic behavior" of multiplicative/dual-norm algorithms. An initial theoretical analysis is provided suggesting that our algorithm might be viewed as a standard Perceptron algorithm operating on a transformed sequence of examples with improved margin properties. We also report on experiments carried out on datasets from diverse domains, with the goal of comparing to known Perceptron algorithms (first-order, second-order, additive, multiplicative). Our learning procedure seems to generalize quite well, and converges faster than the corresponding multiplicative baseline algorithms."

This work concerns estimation of multidimensional nonlinear regression models using multilayer perceptron (MLP). The main problem with such model is that we have to know the covariance matrix of the noise to get optimal estimator. however we show that, if we choose as cost function the logarithm of the determinant of the empirical error covariance matrix, we get an asymptotically optimal estimator.