Combining STDP and binary networks for reinforcement learning from images and sparse rewards.

Spiking neural networks (SNNs) aim to replicate energy efficiency, learning speed and temporal processing of biological brains. However, accuracy and learning speed of such networks is still behind reinforcement learning (RL) models based on traditional neural models. This work combines a pre-trained binary convolutional neural network with an SNN trained online through reward-modulated STDP in order to leverage advantages of both models. The spiking network is an extension of its previous version, with improvements in architecture and dynamics to address a more challenging task. We focus on extensive experimental evaluation of the proposed model with optimized state-of-the-art baselines, namely proximal policy optimization (PPO) and deep Q network (DQN). The models are compared on a grid-world environment with high dimensional observations, consisting of RGB images with up to 256 × 256 pixels. The experimental results show that the proposed architecture can be a competitive alternative to deep reinforcement learning (DRL) in the evaluated environment and provide a foundation for more complex future applications of spiking networks.

Implementing Any Nonlinear Quantum Neuron.

The ability of artificial neural networks (ANNs) to adapt to input data and perform generalizations is intimately connected to the use of nonlinear activation and propagation functions. Quantum versions of ANN have been proposed to take advantage of the possible supremacy of quantum over classical computing. To date, all proposals faced the difficulty of implementing nonlinear activation functions since quantum operators are linear. This brief presents an architecture to simulate the computation of an arbitrary nonlinear function as a quantum circuit. This computation is performed on the phase of an adequately designed quantum state, and quantum phase estimation recovers the result, given a fixed precision, in a circuit with linear complexity in function of ANN input size.

Clustering cancer gene expression data: a comparative study.

BACKGROUND: The use of clustering methods for the discovery of cancer subtypes has drawn a great deal of attention in the scientific community. While bioinformaticians have proposed new clustering methods that take advantage of characteristics of the gene expression data, the medical community has a preference for using "classic" clustering methods. There have been no studies thus far performing a large-scale evaluation of different clustering methods in this context. RESULTS/CONCLUSION: We present the first large-scale analysis of seven different clustering methods and four proximity measures for the analysis of 35 cancer gene expression data sets. Our results reveal that the finite mixture of Gaussians, followed closely by k-means, exhibited the best performance in terms of recovering the true structure of the data sets. These methods also exhibited, on average, the smallest difference between the actual number of classes in the data sets and the best number of clusters as indicated by our validation criteria. Furthermore, hierarchical methods, which have been widely used by the medical community, exhibited a poorer recovery performance than that of the other methods evaluated. Moreover, as a stable basis for the assessment and comparison of different clustering methods for cancer gene expression data, this study provides a common group of data sets (benchmark data sets) to be shared among researchers and used for comparisons with new methods. The data sets analyzed in this study are available at http://algorithmics.molgen.mpg.de/Supplements/CompCancer/.

Clustering and co-evolution to construct neural network ensembles: an experimental study.

This paper introduces an approach called Clustering and Co-evolution to Construct Neural Network Ensembles (CONE). This approach creates neural network ensembles in an innovative way, by explicitly partitioning the input space through a clustering method. The clustering method allows a reduction in the number of nodes of the neural networks that compose the ensemble, thus reducing the execution time of the learning process. This is an important characteristic especially when evolutionary algorithms are used. The clustering method also ensures that different neural networks specialize in different regions of the input space, working in a divide-and-conquer way, to maintain and improve the accuracy. Besides, the clustering method facilitates the understanding of the system and makes a straightforward distributed implementation possible. The experiments performed with seven classification databases and three different co-evolutionary algorithms show that CONE considerably reduces the execution time without prejudicing (and even improving) the accuracy, even when a distributed implementation is not used.

An optimization methodology for neural network weights and architectures.

This paper introduces a methodology for neural network global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques.

Equivalence between RAM-based neural networks and probabilistic automata.

In this letter, the computational power of a class of random access memory (RAM)-based neural networks, called general single-layer sequential weightless neural networks (GSSWNNs), is analyzed. The theoretical results presented, besides helping the understanding of the temporal behavior of these networks, could also provide useful insights for the developing of new learning algorithms.

Hybrid neural systems for pattern recognition in artificial noses.

This work examines the use of Hybrid Intelligent Systems in the pattern recognition system of an artificial nose. The connectionist approaches Multi-Layer Perceptron and Time Delay Neural Networks, and the hybrid approaches Feature-Weighted Detector and Evolving Neural Fuzzy Networks were investigated. A Wavelet Filter is evaluated as a preprocessing method for odor signals. The signals generated by an artificial nose were composed by an array of conducting polymer sensors and exposed to two different odor databases.

Neural network training with global optimization techniques.

This paper presents an approach of using Simulated Annealing and Tabu Search for the simultaneous optimization of neural network architectures and weights. The problem considered is the odor recognition in an artificial nose. Both methods have produced networks with high classification performance and low complexity. Generalization has been improved by using the backpropagation algorithm for fine tuning. The combination of simple and traditional search methods has shown to be very suitable for generating compact and efficient networks.

Modeling a particular decision process by using a modulatory activation function.

Neuronal groups projecting widely in the brain are being experimentally associated to attention and mood changes. Those groups are known to exert a modulatory effect over other larger groups. On the other hand, some people think of the brain functions as being performed by specialized modular systems. In this work, we propose an architecture of modular nature to explore a particular decision process. We show the importance of the modulatory effect of a special evaluation segment in that process.