A new learning algorithm for Evolving Cascade Neural Networks (ECNNs) is described. An ECNN starts to learn with one input node and then adding new inputs as well as new hidden neurons evolves it. The trained ECNN has a nearly minimal number of input and hidden neurons as well as connections. The algorithm was successfully applied to classify artifacts and normal segments in clinical electroencephalograms (EEGs). The EEG segments were visually labeled by EEG-viewer. The trained ECNN has correctly classified 96.69% of the testing segments. It is slightly better than a standard fully connected neural network.
Central China Normal University（华中师范大学）；Kharkiv National University of Radio Electronics（哈尔科夫国立无线电电子大学）
Neo-fuzzy elements are used as nodes for an evolving cascade system. The proposed system can tune both its parameters and architecture in an online mode. It can be used for solving a wide range of Data Mining tasks (namely time series forecasting). The evolving cascade system with neo-fuzzy nodes can process rather large data sets with high speed and effectiveness.
Sentient Technologies, Inc.（Sentient科技公司）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
The success of deep learning depends on finding an architecture to fit the task. As deep learning has scaled up to more challenging tasks, the architectures have become difficult to design by hand. This paper proposes an automated method, CoDeepNEAT, for optimizing deep learning architectures through evolution. By extending existing neuroevolution methods to topology, components, and hyperparameters, this method achieves results comparable to best human designs in standard benchmarks in object recognition and language modeling. It also supports building a real-world application of automated im…
Insight Centre for Data Analytics（洞察数据分析中心）；University College Dublin（都柏林大学学院）
Multi-label classification is an approach which allows a datapoint to be labelled with more than one class at the same time. A common but trivial approach is to train individual binary classifiers per label, but the performance can be improved by considering associations within the labels. Like with any machine learning algorithm, hyperparameter tuning is important to train a good multi-label classifier model. The task of selecting the best hyperparameter settings for an algorithm is an optimisation problem. Very limited work has been done on automatic hyperparameter tuning and AutoML in the m…
Protein secondary structure prediction is an important problem in bioinformatics. Inspired by the recent successes of deep neural networks, in this paper, we propose an end-to-end deep network that predicts protein secondary structures from integrated local and global contextual features. Our deep architecture leverages convolutional neural networks with different kernel sizes to extract multiscale local contextual features. In addition, considering long-range dependencies existing in amino acid sequences, we set up a bidirectional neural network consisting of gated recurrent unit to capture g…
Technical University of Munich（慕尼黑工业大学）；LMU Hospital Grosshadern（路德维希-马克西米利安-慕尼黑大学格罗斯哈德恩医院）
Automatic segmentation of the liver and hepatic lesions is an important step towards deriving quantitative biomarkers for accurate clinical diagnosis and computer-aided decision support systems. This paper presents a method to automatically segment liver and lesions in CT and MRI abdomen images using cascaded fully convolutional neural networks (CFCNs) enabling the segmentation of a large-scale medical trial or quantitative image analysis. We train and cascade two FCNs for a combined segmentation of the liver and its lesions. In the first step, we train a FCN to segment the liver as ROI input …
Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in general, freezing the trained feature extractor (the lower layers) and retraining the classifier (the upper layers) on the same dataset leads to worse performance. In this paper, for the first time, we show that the frozen classifier is transferable within the same dataset. We develop a novel top-down training method which can be viewed as an algorithm for searching for high-quality classifiers. We tested this method on…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very difficult to obtain both coherent and accurate labeling results. For this challenging task, we propose a novel deep model with convolutional neural networks (CNNs), i.e., an end-to-end self-cascaded network (ScasNet). Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation. Tec…
This paper presents a technique called evolving self-supervised neural networks - neural networks that can teach themselves, intrinsically motivated, without external supervision or reward. The proposed method presents some sort-of paradigm shift, and differs greatly from both traditional gradient-based learning and evolutionary algorithms in that it combines the metaphor of evolution and learning, more specifically self-learning, together, rather than treating these phenomena alternatively. I simulate a multi-agent system in which neural networks are used to control autonomous foraging agents…
Kharkiv National University of Radio Electronics（哈尔科夫国立无线电电子大学）
A new architecture and learning algorithms for the multidimensional hybrid cascade neural network with neuron pool optimization in each cascade are proposed in this paper. The proposed system differs from the well-known cascade systems in its capability to process multidimensional time series in an online mode, which makes it possible to process non-stationary stochastic and chaotic signals with the required accuracy. Compared to conventional analogs, the proposed system provides computational simplicity and possesses both tracking and filtering capabilities.
Recent developments within memory-augmented neural networks have solved sequential problems requiring long-term memory, which are intractable for traditional neural networks. However, current approaches still struggle to scale to large memory sizes and sequence lengths. In this paper we show how access to memory can be encoded geometrically through a HyperNEAT-based Neural Turing Machine (HyperENTM). We demonstrate that using the indirect HyperNEAT encoding allows for training on small memory vectors in a bit-vector copy task and then applying the knowledge gained from such training to speed u…
Inspired by the natural nervous system, synaptic plasticity rules are applied to train spiking neural networks with local information, making them suitable for online learning on neuromorphic hardware. However, when such rules are implemented to learn different new tasks, they usually require a significant amount of work on task-dependent fine-tuning. This paper aims to make this process easier by employing an evolutionary algorithm that evolves suitable synaptic plasticity rules for the task at hand. More specifically, we provide a set of various local signals, a set of mathematical operators…
The so-called Baldwin Effect generally says how learning, as a form of ontogenetic adaptation, can influence the process of phylogenetic adaptation, or evolution. This idea has also been taken into computation in which evolution and learning are used as computational metaphors, including evolving neural networks. This paper presents a technique called evolving self-taught neural networks - neural networks that can teach themselves without external supervision or reward. The self-taught neural network is intrinsically motivated. Moreover, the self-taught neural network is the product of the int…
Humans are not only adept in recognizing what class an input instance belongs to (i.e., classification task), but perhaps more remarkably, they can imagine (i.e., generate) plausible instances of a desired class with ease, when prompted. Inspired by this, we propose a framework which allows transforming Cascade-Correlation Neural Networks (CCNNs) into probabilistic generative models, thereby enabling CCNNs to generate samples from a category of interest. CCNNs are a well-known class of deterministic, discriminative NNs, which autonomously construct their topology, and have been successful in g…
Surface plasmon polaritons (SPPs) confined along metal-dielectric interface have attracted a relevant interest in the area of ultracompact photonic circuits, photovoltaic devices and other applications due to their strong field confinement and enhancement. This paper investigates a novel cascade neural network (NN) architecture to find the dependance of metal thickness on the SPP propagation. Additionally, a novel training procedure for the proposed cascade NN has been developed using an OpenMP-based framework, thus greatly reducing training time. The performed experiments confirm the effectiv…
Centrum Wiskunde & Informatica（荷兰国家数学与计算机科学研究所）；Leiden University Medical Center（莱顿大学医学中心）；TU Delft（代尔夫特理工大学）
To achieve excellent performance with modern neural networks, having the right network architecture is important. Neural Architecture Search (NAS) concerns the automatic discovery of task-specific network architectures. Modern NAS approaches leverage supernetworks whose subnetworks encode candidate neural network architectures. These subnetworks can be trained simultaneously, removing the need to train each network from scratch, thereby increasing the efficiency of NAS. A recent method called Neural Architecture Transfer (NAT) further improves the efficiency of NAS for computer vision tasks by…
The adaptive learning capabilities seen in biological neural networks are largely a product of the self-modifying behavior emerging from online plastic changes in synaptic connectivity. Current methods in Reinforcement Learning (RL) only adjust to new interactions after reflection over a specified time interval, preventing the emergence of online adaptivity. Recent work addressing this by endowing artificial neural networks with neuromodulated plasticity have been shown to improve performance on simple RL tasks trained using backpropagation, but have yet to scale up to larger problems. Here we…
Collaborative Filtering (CF) is widely used in recommender systems to model user-item interactions. With the great success of Deep Neural Networks (DNNs) in various fields, advanced works recently have proposed several DNN-based models for CF, which have been proven effective. However, the neural networks are all designed manually. As a consequence, it requires the designers to develop expertise in both CF and DNNs, which limits the application of deep learning methods in CF and the accuracy of recommended results. In this paper, we introduce the genetic algorithm into the process of designing…
Machine Learning (ML) is becoming increasingly important in daily life. In this context, Artificial Neural Networks (ANNs) are a popular approach within ML methods to realize an artificial intelligence. Usually, the topology of ANNs is predetermined. However, there are problems where it is difficult to find a suitable topology. Therefore, Topology and Weight Evolving Artificial Neural Network (TWEANN) algorithms have been developed that can find ANN topologies and weights using genetic algorithms. A well-known downside for large-scale problems is that TWEANN algorithms often evolve inefficient…
In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.
We investigate Turing's notion of an A-type artificial neural network. We study a refinement of Turing's original idea, motivated by work of Teuscher, Bull, Preen and Copeland. Our A-types can process binary data by accepting and outputting sequences of binary vectors; hence we can associate a function to an A-type, and we say the A-type {\em represents} the function. There are two modes of data processing: clamped and sequential. We describe an evolutionary algorithm, involving graph-theoretic manipulations of A-types, which searches for A-types representing a given function. The algorithm us…
Deep Convolutional Neural Networks (CNNs) have been widely used in image classification tasks, but the process of designing CNN architectures is very complex, so Neural Architecture Search (NAS), automatically searching for optimal CNN architectures, has attracted more and more research interests. However, the computational cost of NAS is often too high to apply NAS on real-life applications. In this paper, an efficient particle swarm optimisation method named EPSOCNN is proposed to evolve CNN architectures inspired by the idea of transfer learning. EPSOCNN successfully reduces the computation…
University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））
Neural networks are gaining popularity in the reinforcement learning field due to the vast number of successfully solved complex benchmark problems. In fact, artificial intelligence algorithms are, in some cases, able to overcome human professionals. Usually, neural networks have more than a couple of hidden layers, and thus, they involve a large quantity of parameters that need to be optimized. Commonly, numeric approaches are used to optimize the inner parameters of neural networks, such as the stochastic gradient descent. However, these techniques tend to be computationally very expensive, …
Though machine learning has been applied to the foreign exchange market for algorithmic trading for quiet some time now, and neural networks(NN) have been shown to yield positive results, in most modern approaches the NN systems are optimized through traditional methods like the backpropagation algorithm for example, and their input signals are price lists, and lists composed of other technical indicator elements. The aim of this paper is twofold: the presentation and testing of the application of topology and weight evolving artificial neural network (TWEANN) systems to automated currency tra…
Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights. In this paper, we propose a new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems. In the proposed algorithm, an efficient variable-length gene encoding strategy is designed to represent the different bu…
Neuromorphic computing --- brainlike computing in hardware --- typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently citepd as strong synapse candidates due to their statefulness and potential for low-power implementations. To date, plentiful research has focused on the bipolar memristor synapse, which is capable of incremental weight alterations and can provide adaptive self-organisation under a Hebbian learning scheme. In this paper we consider the Unipolar memristor synapse --- a device capable of non-Hebbian s…
Evolving Neural Networks (NNs) has recently seen an increasing interest as an alternative path that might be more successful. It has many advantages compared to other approaches, such as learning the architecture of the NNs. However, the extremely large search space and the existence of many complex interacting parts still represent a major obstacle. Many criteria were recently investigated to help guide the algorithm and to cut down the large search space. Recently there has been growing research bringing insights from network science to improve the design of NNs. In this paper, we investigat…
The University of New South Wales at the Australian Defence Force Academy（新南威尔士大学澳大利亚国防军学院分校）；DATA61 at CSIRO（澳大利亚联邦科学与工业研究组织DATA61部门）
Spiking Neural Networks are powerful computational modelling tools that have attracted much interest because of the bioinspired modelling of synaptic interactions between neurons. Most of the research employing spiking neurons has been non-behavioural and discontinuous. Comparatively, this paper presents a recurrent spiking controller that is capable of solving nonlinear control problems in continuous domains using a popular topology evolution algorithm as the learning mechanism. We propose two mechanisms necessary to the decoding of continuous signals from discrete spike transmission: (i) a b…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Massachusetts Institute of Technology（麻省理工学院）；Amherst College（阿默斯特学院）；Hampshire College（汉普郡学院）
Over-parameterization is one of the inherent characteristics of modern deep neural networks, which can often be overcome by leveraging regularization methods, such as Dropout. Usually, these methods are applied globally and all the input cases are treated equally. However, given the natural variation of the input space for real-world tasks such as image recognition and natural language understanding, it is unlikely that a fixed regularization pattern will have the same effectiveness for all the input cases. In this work, we demonstrate a method in which the selection of neurons in deep neural …
Although Deep Neural Networks have seen great success in recent years through various changes in overall architectures and optimization strategies, their fundamental underlying design remains largely unchanged. Computational neuroscience on the other hand provides more biologically realistic models of neural processing mechanisms, but they are still high level abstractions of the actual experimentally observed behaviour. Here a model is proposed that bridges Neuroscience, Machine Learning and Evolutionary Algorithms to evolve individual soma and synaptic compartment models of neurons in a scal…
Neural Architecture Search (NAS) has significantly improved productivity in the design and deployment of neural networks (NN). As NAS typically evaluates multiple models by training them partially or completely, the improved productivity comes at the cost of significant carbon footprint. To alleviate this expensive training routine, zero-shot/cost proxies analyze an NN at initialization to generate a score, which correlates highly with its true accuracy. Zero-cost proxies are currently designed by experts conducting multiple cycles of empirical testing on possible algorithms, datasets, and neu…
