查看更多>>摘要：? 2021 Elsevier LtdMulti-view clustering has become an active topic in artificial intelligence. Yet, similar investigation for graph-structured data clustering has been absent so far. To fill this gap, we present a Multi-View Graph embedding Clustering network (MVGC). Specifically, unlike traditional multi-view construction methods, which are only suitable to describe Euclidean structure data, we leverage Euler transform to augment the node attribute, as a new view descriptor, for non-Euclidean structure data. Meanwhile, we impose block diagonal representation constraint, which is measured by the ?1,2-norm, on self-expression coefficient matrix to well explore the cluster structure. By doing so, the learned view-consensus coefficient matrix well encodes the discriminative information. Moreover, we make use of the learned clustering labels to guide the learnings of node representation and coefficient matrix, where the latter is used in turn to conduct the subsequent clustering. In this way, clustering and representation learning are seamlessly connected, with the aim to achieve better clustering performance. Extensive experimental results indicate that MVGC is superior to 11 state-of-the-art methods on four benchmark datasets. In particular, MVGC achieves an Accuracy of 96.17% (53.31%) on the ACM (IMDB) dataset, which is an up to 2.85% (1.97%) clustering performance improvement compared with the strongest baseline.
查看更多>>摘要：? 2021 The Author(s)In neuroscience, attention has been shown to bidirectionally interact with reinforcement learning (RL) to reduce the dimensionality of task representations, restricting computations to relevant features. In machine learning, despite their popularity, attention mechanisms have seldom been administered to decision-making problems. Here, we leverage a theoretical model from computational neuroscience – the attention-weighted RL (AWRL), defining how humans identify task-relevant features (i.e., that allow value predictions) – to design an applied deep RL paradigm. We formally demonstrate that the conjunction of the self-attention mechanism, widely employed in machine learning, with value function approximation is a general formulation of the AWRL model. To evaluate our agent, we train it on three Atari tasks at different complexity levels, incorporating both task-relevant and irrelevant features. Because the model uses semantic observations, we can uncover not only which features the agent elects to base decisions on, but also how it chooses to compile more complex, relational features from simpler ones. We first show that performance depends in large part on the ability to compile new compound features, rather than mere focus on individual features. In line with neuroscience predictions, self-attention leads to high resiliency to noise (irrelevant features) compared to other benchmark models. Finally, we highlight the importance and separate contributions of both bottom-up and top-down attention in the learning process. Together, these results demonstrate the broader validity of the AWRL framework in complex task scenarios, and illustrate the benefits of a deeper integration between neuroscience-derived models and RL for decision making in machine learning.
查看更多>>摘要：? 2021 Elsevier LtdCode search is a common practice for developers during software implementation. The challenges of accurate code search mainly lie in the knowledge gap between source code and natural language (i.e., queries). Due to the limited code-query pairs and large code-description pairs available, the prior studies based on deep learning techniques focus on learning the semantic matching relation between source code and corresponding description texts for the task, and hypothesize that the semantic gap between descriptions and user queries is marginal. In this work, we found that the code search models trained on code-description pairs may not perform well on user queries, which indicates the semantic distance between queries and code descriptions. To mitigate the semantic distance for more effective code search, we propose QueCos, a Query-enriched Code search model. QueCos learns to generate semantic enriched queries to capture the key semantics of given queries with reinforcement learning (RL). With RL, the code search performance is considered as a reward for producing accurate semantic enriched queries. The enriched queries are finally employed for code search. Experiments on the benchmark datasets show that QueCos can significantly outperform the state-of-the-art code search models.
查看更多>>摘要：? 2021 Elsevier LtdIn this paper, a complementary learning scheme for experience transference of unknown continuous-time linear systems is proposed. The algorithm is inspired in the complementary learning properties that exhibit the hippocampus and neocortex learning systems via the striatum. The hippocampus is modelled as pattern-separated data of a human optimized controller. The neocortex is modelled as a Q-reinforcement learning algorithm which improves the hippocampus control policy. The complementary learning (striatum) is designed as an inverse reinforcement learning algorithm which relates the hippocampus and neocortex learning models to seek and transfer the weights of the hidden expert's utility function. Convergence of the proposed approach is analysed using Lyapunov recursions. Simulations are given to verify the proposed approach.
查看更多>>摘要：? 2021 Elsevier LtdIn this paper we introduce a biologically inspired Convolutional Neural Network (CNN) architecture called LGN-CNN that has a first convolutional layer composed of a single filter that mimics the role of the Lateral Geniculate Nucleus (LGN). The first layer of the neural network shows a rotational symmetric pattern justified by the structure of the net itself that turns up to be an approximation of a Laplacian of Gaussian (LoG). The latter function is in turn a good approximation of the receptive field profiles (RFPs) of the cells in the LGN. The analogy with the visual system is established, emerging directly from the architecture of the neural network. A proof of rotation invariance of the first layer is given on a fixed LGN-CNN architecture and the computational results are shown. Thus, contrast invariance capability of the LGN-CNN is investigated and a comparison between the Retinex effects of the first layer of LGN-CNN and the Retinex effects of a LoG is provided on different images. A statistical study is done on the filters of the second convolutional layer with respect to biological data. In conclusion, the model we have introduced approximates well the RFPs of both LGN and V1 attaining similar behavior as regards long range connections of LGN cells that show Retinex effects.
查看更多>>摘要：? 2021 Elsevier LtdThere is limited study in the literature on the representability of neural networks on unbounded domains. For some application areas, results in this direction provide additional value in the design of learning systems. Motivated by an old option pricing problem, we are led to the study of this subject. For networks with a single hidden layer, we show that under suitable conditions they are capable of universal approximation in Lp(R×[0,1]n) but not in Lp(R2×[0,1]n). For deeper networks, we prove that the ReLU network with two hidden layers is a universal approximator in Lp(Rn).
查看更多>>摘要：? 2021 Elsevier LtdPortfolio optimization is one of the most important investment strategies in financial markets. It is practically desirable for investors, especially high-frequency traders, to consider cardinality constraints in portfolio selection, to avoid odd lots and excessive costs such as transaction fees. In this paper, a collaborative neurodynamic optimization approach is presented for cardinality-constrained portfolio selection. The expected return and investment risk in the Markowitz framework are scalarized as a weighted Chebyshev function and the cardinality constraints are equivalently represented using introduced binary variables as an upper bound. Then cardinality-constrained portfolio selection is formulated as a mixed-integer optimization problem and solved by means of collaborative neurodynamic optimization with multiple recurrent neural networks repeatedly repositioned using a particle swarm optimization rule. The distribution of resulting Pareto-optimal solutions is also iteratively perfected by optimizing the weights in the scalarized objective functions based on particle swarm optimization. Experimental results with stock data from four major world markets are discussed to substantiate the superior performance of the collaborative neurodynamic approach to several exact and metaheuristic methods.
查看更多>>摘要：? 2021 The Author(s)The intersection between neuroscience and artificial intelligence (AI) research has created synergistic effects in both fields. While neuroscientific discoveries have inspired the development of AI architectures, new ideas and algorithms from AI research have produced new ways to study brain mechanisms. A well-known example is the case of reinforcement learning (RL), which has stimulated neuroscience research on how animals learn to adjust their behavior to maximize reward. In this review article, we cover recent collaborative work between the two fields in the context of meta-learning and its extension to social cognition and consciousness. Meta-learning refers to the ability to learn how to learn, such as learning to adjust hyperparameters of existing learning algorithms and how to use existing models and knowledge to efficiently solve new tasks. This meta-learning capability is important for making existing AI systems more adaptive and flexible to efficiently solve new tasks. Since this is one of the areas where there is a gap between human performance and current AI systems, successful collaboration should produce new ideas and progress. Starting from the role of RL algorithms in driving neuroscience, we discuss recent developments in deep RL applied to modeling prefrontal cortex functions. Even from a broader perspective, we discuss the similarities and differences between social cognition and meta-learning, and finally conclude with speculations on the potential links between intelligence as endowed by model-based RL and consciousness. For future work we highlight data efficiency, autonomy and intrinsic motivation as key research areas for advancing both fields.
查看更多>>摘要：? 2021 The AuthorsWe introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets. Our theoretical analysis shows that ICT corresponds to a certain type of data-adaptive regularization with unlabeled points which reduces overfitting to labeled points under high confidence values.
查看更多>>摘要：? 2021 The AuthorsIt is one of the ultimate goals of ethology to understand the generative process of animal behavior, and the ability to reproduce and control behavior is an important step in this field. However, it is not easy to achieve this goal in systems with complex and stochastic dynamics such as animal behavior. In this study, we have shown that MDN–RNN,a type of probabilistic deep generative model, is able to reproduce stochastic animal behavior with high accuracy by modeling the behavior of C. elegans. Furthermore, we found that the model learns different dynamics in a disentangled representation as a time-evolving Gaussian mixture. Finally, by combining the model and reinforcement learning, we were able to extract a behavioral policy of goal-directed behavior in silico, and showed that it can be used for regulating the behavior of real animals. This set of methods will be applicable not only to animal behavior but also to broader areas such as neuroscience and robotics.
NSTL
Elsevier