The feasibility of directly implementing the learned neural network into the real manipulator is confirmed by a dynamic obstacle avoidance challenge.

Image classification using supervised learning of very complex neural networks, while achieving cutting-edge results, often exhibits excessive fitting to the training data, thus compromising its ability to generalize well to unseen instances. By incorporating soft targets as additional training signals, output regularization manages overfitting. While clustering serves as a cornerstone in data analysis for uncovering underlying patterns, current output regularization methods have overlooked its potential. By proposing Cluster-based soft targets for Output Regularization (CluOReg), this article leverages the structural information that underlies the data. This approach, leveraging cluster-based soft targets via output regularization, unifies simultaneous clustering in embedding space and neural classifier training procedures. The calculation of a class-relationship matrix in the cluster space allows us to obtain class-specific soft targets applicable across all samples within a given class. Results from image classification experiments are presented for a number of benchmark datasets under various setup conditions. We achieve consistent and noteworthy reductions in classification error, outperforming other methods without the use of external models or designed data augmentation. This exemplifies the effectiveness of cluster-based soft targets in supporting ground-truth labels.

The segmentation of planar regions using existing methods often suffers from blurred boundaries and a failure to identify smaller regions. In order to resolve these challenges, this study presents a complete end-to-end framework called PlaneSeg, easily applicable to a variety of plane segmentation models. PlaneSeg's architecture is structured around three distinct modules: edge feature extraction, multiscale processing, and resolution adaptation. The edge feature extraction module's output are feature maps that recognize edges, leading to a more detailed segmentation. The acquired boundary knowledge acts as a restriction, minimizing the likelihood of incorrect delimitations. To begin with, the multiscale module assimilates feature maps from varying layers, thereby harvesting spatial and semantic information from planar objects. The multitude of object attributes assists in the identification of compact objects, contributing to more accurate segmentation. At the third stage, the resolution-adaptation module synthesizes the feature maps from the two previously described modules. To resample the missing pixels and extract more intricate features within this module, a pairwise feature fusion strategy is employed. PlaneSeg's superior performance in plane segmentation, 3-D plane reconstruction, and depth prediction, as demonstrated by a wealth of experimentation, clearly positions it above competing state-of-the-art methods. Within the PlaneSeg project, the code is downloadable from the GitHub repository at https://github.com/nku-zhichengzhang/PlaneSeg.

Graph clustering applications are intrinsically linked to the graph's representation. In graph representation, contrastive learning, a recently popular and powerful method, maximizes the mutual information between augmented graph views that inherently share the same semantics. Although patch contrasting methods often assimilate all features into comparable variables, resulting in representation collapse and less effective graph representations, existing literature frequently overlooks this issue. This problem is tackled using a novel self-supervised learning method, the Dual Contrastive Learning Network (DCLN), aiming to reduce the redundant information of learned latent variables using a dual learning paradigm. The dual curriculum contrastive module (DCCM), a novel approach, approximates the feature similarity matrix by an identity matrix and the node similarity matrix by a high-order adjacency matrix. Applying this technique, the significant information from high-order neighbors is effectively collected and preserved, while the superfluous and redundant characteristics within the representations are eliminated, thus enhancing the discriminative ability of the graph representation. Additionally, to remedy the sample imbalance problem in the contrastive learning process, we develop a curriculum learning strategy, enabling the network to simultaneously learn valuable information from two hierarchical levels. Benchmark datasets, each comprising six distinct categories, underwent comprehensive testing, conclusively demonstrating the proposed algorithm's superior effectiveness and advantage over current state-of-the-art methods.

To enhance generalization in deep learning and automate learning rate scheduling, we introduce SALR, a sharpness-aware learning rate adjustment method, designed to find flat minima. The local sharpness of the loss function informs the dynamic learning rate adjustments implemented by our method for gradient-based optimizers. To improve their chance of escaping sharp valleys, optimizers can automatically enhance their learning rates. Across a broad array of networks and algorithms, SALR's efficacy is evident. The outcomes of our experiments highlight SALR's ability to enhance generalization, accelerate convergence, and drive solutions towards significantly flatter minima.

The long oil pipeline system's success is intimately tied to the effectiveness of magnetic leakage detection technology. Effective magnetic flux leakage (MFL) detection relies on the automatic segmentation of images showing defects. Precisely segmenting tiny defects has historically been a significant hurdle. Different from the current leading MFL detection methodologies employing convolutional neural networks (CNNs), our study proposes an optimization strategy by integrating mask region-based CNNs (Mask R-CNN) and information entropy constraints (IEC). The convolution kernel's feature learning and network segmentation are enhanced through the use of principal component analysis (PCA). Biosafety protection The Mask R-CNN network's convolution layer is proposed to incorporate the similarity constraint rule of information entropy. Mask R-CNN's convolutional kernels are optimized with weights that are similar or more alike; concurrently, the PCA network reduces the feature image's dimensionality to re-create its original vector representation. For MFL defects, the convolution check is utilized for optimized feature extraction. MFL detection methods can be enhanced using the research data.

Through the implementation of smart systems, artificial neural networks (ANNs) have achieved widespread use. see more The energy-intensive nature of conventional artificial neural network implementations restricts their application in mobile and embedded systems. The temporal information flow in biological neural networks is mimicked by spiking neural networks (SNNs), using binary spikes to distribute information over time. Neuromorphic hardware, capitalizing on the attributes of SNNs, effectively utilizes asynchronous processing and high activation sparsity. In conclusion, SNNs have experienced a surge in the machine learning community's interest, providing a brain-like architecture alternative to ANNs, which is particularly beneficial for low-power applications. Although the discrete representation is fundamental to SNNs, it complicates the training process using backpropagation-based techniques. This survey investigates training strategies for deep spiking neural networks, targeting deep learning tasks such as image processing. We begin with methods originating from the transformation of an artificial neural network into a spiking neural network, and afterwards, we will evaluate them against backpropagation-based methods. We formulate a new taxonomy for spiking backpropagation algorithms, comprising the spatial, spatiotemporal, and single-spike categories. We additionally examine diverse tactics to boost accuracy, latency, and sparsity, including regularization strategies, training hybridization techniques, and parameter tuning unique to the SNN neuron model. We dissect the relationship between input encoding, network architecture, and training strategy and their consequences for the accuracy-latency trade-off. In summary, facing the ongoing difficulties in developing accurate and efficient implementations of spiking neural networks, we stress the need for concurrent hardware-software engineering.

The Vision Transformer (ViT) signifies a paradigm shift, showcasing the capacity of transformer models to transcend traditional boundaries by successfully processing images. In a process of fragmentation, the model separates an image into many small sections and then arranges these sections into a sequential sequence. Learning the attentional relationships between the sequence's patches is accomplished by applying multi-head self-attention. Although transformer models have shown promising results in analyzing sequential data, their counterparts, Vision Transformers, lack comparable scrutiny in their interpretation, leading to numerous unanswered questions. From the plethora of attention heads, which one holds the most import? Evaluating the potency of the influence of spatial neighbors on individual patches, within the context of distinct computational heads, how substantial is the impact? Which attention patterns have individual heads acquired? We address these inquiries using a visual analytics methodology in this study. Specifically, we initially ascertain which heads in ViTs are paramount by introducing various metrics rooted in pruning. Medical image Following this, we analyze the spatial dispersion of attention magnitudes within individual head patches, and the pattern of attention magnitudes across all the attention layers. Third, all potential attention patterns that individual heads could learn are summarized through an autoencoder-based learning solution. Important heads' attention strengths and patterns are examined to determine why they are crucial. By examining real-world examples alongside leading deep learning specialists focusing on various Vision Transformers, we verify the efficacy of our solution, providing a deeper comprehension of Vision Transformers through analysis of head significance, attention strength within heads, and attention patterns.