As an compare non-parametric probability distributions by exploiting instantiation application, we propose a novel machine learning the geometry of the underlying metric space. To name a few, paradigm based on adaptive optimal transport. It conducts optimal transport plays a crucial role in a wide variety of the partial distribution alignment between source and target machine learning applications, such as generative adversarial domains by treating the noises, outliers, and distribution shifts networks [1], computer vision [2], natural language processing in a principled way. Furthermore, we investigate the mass [3], clustering [4], semi-supervised learning [5], and domain allocation mechanism of adaptive optimal transport and derive adaptation [6]. The essential problem in these applications is the duality theory. The theoretical analysis provides insights how to compare two probability distributions such as aligning into adaptive optimal transport and reinforces its mathematical the fake images with the real images, aligning images with foundation. We believe that adaptive optimal transport is of audio, or aligning the AI generated content with human great interests to the broad areas such as artificial intelligence, feedback in large language model.

A swarm intelligence-based optimization algorithm, named Duck Swarm Algorithm (DSA), is proposed in this paper. This algorithm is inspired by the searching for food sources and foraging behaviors of the duck swarm. The performance of DSA is verified by using eighteen benchmark functions, where it is statistical (best, mean, standard deviation, and average running time) results are compared with seven well-known algorithms like Particle swarm optimization (PSO), Firefly algorithm (FA), Chicken swarm optimization (CSO), Grey wolf optimizer (GWO), Sine cosine algorithm (SCA), and Marine-predators algorithm (MPA), and Archimedes optimization algorithm (AOA). Moreover, the Wilcoxon rank-sum test, Friedman test, and convergence curves of the comparison results are used to prove the superiority of the DSA against other algorithms. The results demonstrate that DSA is a high-performance optimization method in terms of convergence speed and exploration-exploitation balance for solving high-dimension optimization functions. Also, DSA is applied for the optimal design of two constrained engineering problems (the Three-bar truss problem, and the Sawmill operation problem). Additionally, four engineering constraint problems have also been used to analyze the performance of the proposed DSA. Overall, the comparison results revealed that the DSA is a promising and very competitive algorithm for solving different optimization problems.

Supervised machine learning has several drawbacks that make it difficult to use in many situations. Drawbacks include: heavy reliance on massive training data, limited generalizability and poor expressiveness of high-level semantics. Low-shot Learning attempts to address these drawbacks. Low-shot learning allows the model to obtain good predictive power with very little or no training data, where structured knowledge plays a key role as a high-level semantic representation of human. This article will review the fundamental factors of low-shot learning technologies, with a focus on the operation of structured knowledge under different low-shot conditions. We also introduce other techniques relevant to low-shot learning. Finally, we point out the limitations of low-shot learning, the prospects and gaps of industrial applications, and future research directions.

Residual Networks make the very deep convolutional architecture works well, which use the residual unit to supplement the identity mappings. On the other hand, Squeeze-Excitation (SE) network propose an adaptively recalibrates channel-wise attention approach to model the relationship of feature maps from different convolutional channel. In this work, we propose the competitive SE mechanism for residual network, rescaling value for each channel in this structure will be determined by residual and identity mappings jointly, this design enables us to expand the meaning of channel relationship modeling in residual blocks: the modeling of competition between residual and identity mappings make identity flow can controll the complement of residual feature maps for itself. Further, we design a novel pair-view competitive SE block to shrink the consumption and re-image the global characterizations of intermediate convolutional channels. We carry out experiments on datasets: CIFAR, SVHN, ImageNet, the proposed method can be compared with the state-of-the-art results.

Recently, hashing methods have been widely used in large-scale image retrieval. However, most existing supervised hashing methods do not consider the hierarchical relation of labels,which means that they ignored the rich semantic information stored in the hierarchy. Moreover, most of previous works treat each bit in a hash code equally, which does not meet the scenario of hierarchical labeled data. To tackle the aforementioned problems, in this paper, we propose a novel deep hashing method, called supervised hierarchical deep hashing (SHDH), to perform hash code learning for hierarchical labeled data. Specifically, we define a novel similarity formula for hierarchical labeled data by weighting each level, and design a deep neural network to obtain a hash code for each data point. Extensive experiments on two real-world public datasets show that the proposed method outperforms the state-of-the-art baselines in the image retrieval task.

To compare the similarity of probability distributions, the information-theoretically motivated metrics like Kullback-Leibler divergence (KL) and Jensen-Shannon divergence (JSD) are often more reasonable compared with metrics for vectors like Euclidean and angular distance. However, existing locality-sensitive hashing (LSH) algorithms cannot support the information-theoretically motivated metrics for probability distributions. In this paper, we first introduce a new approximation formula for S2JSD-distance, and then propose a novel LSH scheme adapted to S2JSD-distance for approximate nearest neighbors search in high-dimensional probability distributions. We define the specific hashing functions, and prove their local-sensitivity. Furthermore, extensive empirical evaluations well illustrate the effectiveness of the proposed hashing schema on six public image datasets and two text datasets, in terms of mean Average Precision, Precision@N and Precision-Recall curve.