Related papers: DynaLay: An Introspective Approach to Dynamic Laye…

Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden…

In modern sequential decision-making systems, the construction of an optimal candidate action space is critical to efficient inference. However, existing approaches either rely on manually defined action spaces that lack scalability or…

Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the…

In recent years, employing layer attention to enhance interaction among hierarchical layers has proven to be a significant advancement in building network structures. In this paper, we delve into the distinction between layer attention and…

In this work, we consider the problem of instance-wise dynamic network model selection for multi-task learning. To this end, we propose an efficient approach to exploit a compact but accurate model in a backbone architecture for each…

Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns. Probabilistic logic reasoning, on the other hand, is capable to take…

Modern computationally-intensive applications often operate under time constraints, necessitating acceleration methods and distribution of computational workloads across multiple entities. However, the outcome is either achieved within the…

Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We introduce Neural Low-Degree Filtering (Neural LoFi), a stylized limit of gradient-based…

Despite deep learning (DL) has achieved remarkable progress in various domains, the DL models are still prone to making mistakes. This issue necessitates effective debugging tools for DL practitioners to interpret the decision-making…

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when…

Deep learning is the backbone of artificial intelligence technologies, and it can be regarded as a kind of multilayer feedforward neural network. An essence of deep learning is information propagation through layers. This suggests that…

Deep learning has shown promising results in many machine learning applications. The hierarchical feature representation built by deep networks enable compact and precise encoding of the data. A kernel analysis of the trained deep networks…

Deep neural networks ( DNNs ) are becoming a key enabling technology for many application domains. However, on-device inference on battery-powered, resource-constrained embedding systems is often infeasible due to prohibitively long…

Artificial intelligence (AI) has evolved into an ecosystem of specialized "species," each with unique strengths. We analyze two: DeepSeek-V3, a 671-billion-parameter Mixture of Experts large language model (LLM) exemplifying scale-driven…

This paper investigates how adjustments to deep learning architectures impact model performance in image classification. Small-scale experiments generate initial insights although the trends observed are not consistent with the entire…

Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to improve their efficiency, enabling them to reach high…

Deep learning is vulnerable to adversarial attacks, where carefully-crafted input perturbations could mislead a well-trained Deep Neural Network to produce incorrect results. Today's countermeasures to adversarial attacks either do not have…

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

We propose a novel explanation method that explains the decisions of a deep neural network by investigating how the intermediate representations at each layer of the deep network were refined during the training process. This way we can a)…

This article explores the design and experimentation of a neural network architecture capable of dynamically adjusting its internal structure based on the input data. The proposed model introduces a routing mechanism that allows each layer…