Computer Science - Neural and Evolutionary Computing Publications (50)


Computer Science - Neural and Evolutionary Computing Publications

Grammatical Evolution (GE) is a population-based evolutionary algorithm, where a formal grammar is used in the genotype to phenotype mapping process. PonyGE2 is an open source implementation of GE in Python, developed at UCD's Natural Computing Research and Applications group. It is intended as an advertisement and a starting-point for those new to GE, a reference for students and researchers, a rapid-prototyping medium for our own experiments, and a Python workout. Read More

We evolve binary mux-6 trees for up to 100000 generations evolving some programs with more than a hundred million nodes. Our unbounded Long-Term Evolution Experiment LTEE GP appears not to evolve building blocks but does suggests a limit to bloat. We do see periods of tens even hundreds of generations where the population is 100 percent functionally converged. Read More

Deep neural networks achieve unprecedented performance levels over many tasks and scale well with large quantities of data, but performance in the low-data regime and tasks like one shot learning still lags behind. While recent work suggests many hypotheses from better optimization to more complicated network structures, in this work we hypothesize that having a learnable and more expressive similarity objective is an essential missing component. Towards overcoming that, we propose a network design inspired by deep residual networks that allows the efficient computation of this more expressive pairwise similarity objective. Read More

Synapses in real neural circuits can take discrete values, including zero (silent or potential) synapses. The computational role of zero synapses in unsupervised feature learning of unlabeled noisy data is still unclear, yet important to understand how the sparseness of synaptic activity is shaped during learning and its relationship with receptive field formation. Here, we formulate this kind of sparse feature learning by statistical mechanics approach. Read More

A promising approach towards understanding neural networks is to view them as implementations of online algorithms optimizing principled objectives. Existing neural algorithms capturing both neural activity dynamics and synaptic weight updates implement the same operation, either minimization or maximization of the objective, with respect to each variable. Here, we derive neural networks from principled min-max objectives: by minimizing with respect to neural activity and feedforward synaptic weights, and maximizing with respect to lateral synaptic weights. Read More

We report the results of our classification-based machine translation model, built upon the framework of a recurrent neural network using gated recurrent units. Unlike other RNN models that attempt to maximize the overall conditional log probability of sentences against sentences, our model focuses a classification approach of estimating the conditional probability of the next word given the input sequence. This simpler approach using GRUs was hoped to be comparable with more complicated RNN models, but achievements in this implementation were modest and there remains a lot of room for improving this classification approach. Read More

Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences. Such systems are used with a dictionary and separately-trained Language Model (LM) to produce word sequences. However, they are not truly end-to-end in the sense of mapping acoustics directly to words without an intermediate phone representation. Read More

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification subfield is no exception to this, thanks to the notable publication of the Market-1501 and MARS datasets and several strong deep learning approaches. Unfortunately, a prevailing belief in the community seems to be that the triplet loss is inferior to using surrogate losses (classification, verification) followed by a separate metric learning step. Read More

A fundamental feature of learning in animals is the "ability to forget" that allows an organism to perceive, model and make decisions from disparate streams of information and adapt to changing environments. Against this backdrop, we present a novel unsupervised learning mechanism ASP (Adaptive Synaptic Plasticity) for improved recognition with Spiking Neural Networks (SNNs) for real time on-line learning in a dynamic environment. We incorporate an adaptive weight decay mechanism with the traditional Spike Timing Dependent Plasticity (STDP) learning to model adaptivity in SNNs. Read More

In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly modeling the interactions between sets of parameters and the overall quality of the solutions discovered. We demonstrate a novel method, based on learning deep networks, to model the global landscapes of optimization problems. Read More

Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. Read More

This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model. The scalable neuromorphic architecture is extended by the support for multi-compartment models and non-linear dendrites. These features are part of a \SI{65}{\nano\meter} prototype ASIC. Read More

Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, which is important when training networks with a small number of samples. In this work we extend the neuroevolution algorithm NEAT to evolve the activation function of neurons in addition to the topology and weights of the network. The size and performance of networks produced using NEAT with uniform activation in all nodes, or homogenous networks, is compared to networks which contain a mixture of activation functions, or heterogenous networks. Read More

Recently we proposed a general, ensemble-based feature engineering wrapper (FEW) that was paired with a number of machine learning methods to solve regression problems. Here, we adapt FEW for supervised classification and perform a thorough analysis of fitness and survival methods within this framework. Our tests demonstrate that two fitness metrics, one introduced as an adaptation of the silhouette score, outperform the more commonly used Fisher criterion. Read More

Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players perform steps on a dance platform in synchronization with music as directed by on-screen step charts. While many step charts are available in standardized packs, users may grow tired of existing charts, or wish to dance to a song for which no chart exists. Read More

Expressive efficiency is a concept that allows formally reasoning about the representational capacity of deep network architectures. A network architecture is expressively efficient with respect to an alternative architecture if the latter must grow super-linearly in order to represent functions realized by the former. A well-known example is the exponential expressive efficiency of depth, namely, that in many cases shallow networks must grow exponentially large in order to represent functions realized by deep networks. Read More

This paper introduces QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in the network architecture. Read More

The Echo State Network (ESN) is a specific recurrent network, which has gained popularity during the last years. The model has a recurrent network named reservoir, that is fixed during the learning process. The reservoir is used for transforming the input space in a larger space. Read More

Access to electronic health records (EHR) data has motivated computational advances in medical research. However, various concerns, particularly over privacy, can limit access to and collaborative use of EHR data. Sharing synthetic EHR data could mitigate risk. Read More

We investigate a recently proposed model for cortical computation which performs relational inference. It consists of several interconnected, structurally equivalent populations of leaky integrate-and-fire (LIF) neurons, which are trained in a self-organized fashion with spike-timing dependent plasticity (STDP). Despite its robust learning dynamics, the model is susceptible to a problem typical for recurrent networks which use a correlation based (Hebbian) learning rule: if trained with high learning rates, the recurrent connections can cause strong feedback loops in the network dynamics, which lead to the emergence of attractor states. Read More

This paper studies an intelligent ultimate technique for health-monitoring and prognostic of common rotary machine components, particularly bearings. During a run-to-failure experiment, rich unsupervised features from vibration sensory data are extracted by a trained sparse auto-encoder. Then, the correlation of the extracted attributes of the initial samples (presumably healthy at the beginning of the test) with the succeeding samples is calculated and passed through a moving-average filter. Read More

We introduce SIM-CE, an advanced, user-friendly modeling and simulation environment in Simulink for performing multi-scale behavioral analysis of the nervous system of Caenorhabditis elegans (C. elegans). SIM-CE contains an implementation of the mathematical models of C. Read More

Caenorhabditis elegans (C. elegans) illustrated remarkable behavioral plasticities including complex non-associative and associative learning representations. Understanding the principles of such mechanisms presumably leads to constructive inspirations for the design of efficient learning algorithms. Read More

In the evolutionary computation research community, the performance of most evolutionary algorithms (EAs) depends strongly on their implemented coordinate system. However, the commonly used coordinate system is fixed and not well suited for different function landscapes, EAs thus might not search efficiently. To overcome this shortcoming, in this paper we propose a framework, named ACoS, to adaptively tune the coordinate systems in EAs. Read More

Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization. Besides, Dropout can be interpreted as an approximate model aggregation technique, where an exponential number of smaller networks are averaged in order to get a more powerful ensemble. Read More

We propose and systematically evaluate three strategies for training dynamically-routed artificial neural networks: graphs of learned transformations through which different input signals may take different paths. Though some approaches have advantages over others, the resulting networks are often qualitatively similar. We find that, in dynamically-routed networks trained to classify images, layers and branches become specialized to process distinct categories of images. Read More

Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks. In this paper, we review several possibilites to reverse map these architectures to biologically more realistic spiking networks with the aim of emulating them on fast, low-power neuromorphic hardware. Since many of these devices employ analog components, which cannot be perfectly controlled, finding ways to compensate for the resulting effects represents a key challenge. Read More

Motivated by the advantages achieved by implicit analogue net for solving online linear equations, a novel implicit neural model is designed based on conventional explicit gradient neural networks in this letter by introducing a positive-definite mass matrix. In addition to taking the advantages of the implicit neural dynamics, the proposed implicit gradient neural networks can still achieve globally exponential convergence to the unique theoretical solution of linear equations and also global stability even under no-solution and multi-solution situations. Simulative results verify theoretical convergence analysis on the proposed neural dynamics. Read More

A framework for implementing reservoir computing (RC) and extreme learning machines (ELMs), two types of artificial neural networks, based on 1D elementary Cellular Automata (CA) is presented, in which two separate CA rules explicitly implement the minimum computational requirements of the reservoir layer: hyperdimensional projection and short-term memory. CAs are cell-based state machines, which evolve in time in accordance with local rules based on a cells current state and those of its neighbors. Notably, simple single cell shift rules as the memory rule in a fixed edge CA afforded reasonable success in conjunction with a variety of projection rules, potentially significantly reducing the optimal solution search space. Read More

This work presents a new algorithm called evolutionary exploration of augmenting convolutional topologies (EXACT), which is capable of evolving the structure of convolutional neural networks (CNNs). EXACT is in part modeled after the neuroevolution of augmenting topologies (NEAT) algorithm, with notable exceptions to allow it to scale to large scale distributed computing environments and evolve networks with convolutional filters. In addition to multithreaded and MPI versions, EXACT has been implemented as part of a BOINC volunteer computing project, allowing large scale evolution. Read More

Current Deep Learning approaches have been very successful using convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers. Three limitations of this approach are: 1) they are based on a simple layered network topology, i.e. Read More

Programming by Example (PBE) targets at automatically inferring a computer program for accomplishing a certain task from sample input and output. In this paper, we propose a deep neural networks (DNN) based PBE model called Neural Programming by Example (NPBE), which can learn from input-output strings and induce programs that solve the string manipulation problems. Our NPBE model has four neural network based components: a string encoder, an input-output analyzer, a program generator, and a symbol selector. Read More

Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a graph-regularised objective, namely "Neural Graph Machines", that can combine the power of neural networks and label propagation. Read More

Recent development of large-scale question answering (QA) datasets triggered a substantial amount of research into end-to-end neural architectures for QA. Increasingly complex systems have been conceived without comparison to a simpler neural baseline system that would justify their complexity. In this work, we propose a simple heuristic that guided the development of FastQA, an efficient end-to-end neural model for question answering that is very competitive with existing models. Read More

Learning to learn has emerged as an important direction for achieving artificial intelligence. Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks. We introduce a learned gradient descent optimizer that generalizes well to new tasks, and which has significantly reduced memory and computation overhead. Read More

This paper proposes Drone Squadron Optimization, a new self-adaptive metaheuristic for global numerical optimization which is updated online by a hyper-heuristic. DSO is an artifact-inspired technique, as opposed to many algorithms used nowadays, which are nature-inspired. DSO is very flexible because it is not related to behaviors or natural phenomena. Read More

Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to sensors mounted on the robot, sensors might also be deployed in the environment, although these might need to be accessed via an unreliable wireless connection. In this paper, we demonstrate deep neural network architectures that are able to fuse information coming from multiple sensors and are robust to sensor failures at runtime. Read More

Echo state networks are a recently developed type of recurrent neural network where the internal layer is fixed with random weights, and only the output layer is trained on specific data. Echo state networks are increasingly being used to process spatiotemporal data in real-world settings, including speech recognition, event detection, and robot control. A strength of echo state networks is the simple method used to train the output layer - typically a collection of linear readout weights found using a least squares approach. Read More

We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem's geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Read More

In the domain of sequence modelling, Recurrent Neural Networks (RNN) have been capable of achieving impressive results in a variety of application areas including visual question answering, part-of-speech tagging and machine translation. However this success in modelling short term dependencies has not successfully transitioned to application areas such as trajectory prediction, which require capturing both short term and long term relationships. In this paper, we propose a Tree Memory Network (TMN) for modelling long term and short term relationships in sequence-to-sequence mapping problems. Read More

How spiking networks are able to perform probabilistic inference is an intriguing question, not only for understanding information processing in the brain, but also for transferring these computational principles to neuromorphic silicon circuits. A number of computationally powerful spiking network models have been proposed, but most of them have only been tested, under ideal conditions, in software simulations. Any implementation in an analog, physical system, be it in vivo or in silico, will generally lead to distorted dynamics due to the physical properties of the underlying substrate. Read More

Although various norms for reciprocity-based cooperation have been suggested that are evolutionarily stable against invasion from free riders, the process of alternation of norms and the role of diversified norms remain unclear in the evolution of cooperation. We clarify the co-evolutionary dynamics of norms and cooperation in indirect reciprocity and also identify the indispensable norms for the evolution of cooperation. Inspired by the gene knockout method, a genetic engineering technique, we developed the norm knockout method and clarified the norms necessary for the establishment of cooperation. Read More

We examine Memory Networks for the task of question answering (QA), under common real world scenario where training examples are scarce and under weakly supervised scenario, that is only extrinsic labels are available for training. We propose extensions for the Dynamic Memory Network (DMN), specifically within the attention mechanism, we call the resulting Neural Architecture as Dynamic Memory Tensor Network (DMTN). Ultimately, we see that our proposed extensions results in over 80% improvement in the number of task passed against the baselined standard DMN and 20% more task passed compared to state-of-the-art End-to-End Memory Network for Facebook's single task weakly trained 1K bAbi dataset. Read More

We explore the use of Evolution Strategies, a class of black box optimization algorithms, as an alternative to popular RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a viable solution strategy that scales extremely well with the number of CPUs available: By using hundreds to thousands of parallel workers, ES can solve 3D humanoid walking in 10 minutes and obtain competitive results on most Atari games after one hour of training time. In addition, we highlight several advantages of ES as a black box optimization technique: it is invariant to action frequency and delayed rewards, tolerant of extremely long horizons, and does not need temporal discounting or value function approximation. Read More

Brain-inspired learning models attempt to mimic the cortical architecture and computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we present convolutional spike timing dependent plasticity based feature learning with biologically plausible leaky-integrate-and-fire neurons in Spiking Neural Networks (SNNs). We use shared weight kernels that are trained to encode representative features underlying the input patterns thereby improving the sparsity as well as the robustness of the learning model. Read More

Evolutionary algorithms have recently been used to create a wide range of artistic work. In this paper, we propose a new approach for the composition of new images from existing ones, that retain some salient features of the original images. We introduce evolutionary algorithms that create new images based on a fitness function that incorporates feature covariance matrices associated with different parts of the images. Read More

The bound to factor large integers is dominated by the computational effort to discover numbers that are smooth, typically performed by sieving a polynomial sequence. On a von Neumann architecture, sieving has log-log amortized time complexity to check each value for smoothness. This work presents a neuromorphic sieve that achieves a constant time check for smoothness by exploiting two characteristic properties of neuromorphic architectures: constant time synaptic integration and massively parallel computation. Read More

PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. Read More