Related papers: i-Razor: A Differentiable Neural Input Razor for F…

In this paper we evaluate the quality of the activation layers of a convolutional neural network (CNN) for the gen- eration of object proposals. We generate hypotheses in a sliding-window fashion over different activation layers and show…

In machine learning practice it is often useful to identify relevant input features. Isolating key input elements, ranked according their respective degree of relevance, can help to elaborate on the process of decision making. Here, we…

Deep neural networks (DNNs) demonstrate outstanding performance across most computer vision tasks. Some critical applications, such as autonomous driving or medical imaging, also require investigation into their behavior and the reasons…

High-dimensional data is common in multiple areas, such as health care and genomics, where the number of features can be tens of thousands. In such scenarios, the large number of features often leads to inefficient learning. Constraint…

Background: Embedded feature selection in high-dimensional data with very small sample sizes requires optimized hyperparameters for the model building process. For this hyperparameter optimization, nested cross-validation must be applied to…

Beam search is a go-to strategy for decoding neural sequence models. The algorithm can naturally be viewed as a subset optimization problem, albeit one where the corresponding set function does not reflect interactions between candidates.…

Deep recommender systems (DRS) often face challenges in balancing computational efficiency and model accuracy, especially when handling high-dimensional input features. Existing methods either focus on improving accuracy while neglecting…

Unseen noise signal which is not considered in a model training process is difficult to anticipate and would lead to performance degradation. Various methods have been investigated to mitigate unseen noise. In our previous work, an…

Deep reinforcement learning (DRL) has shown remarkable success in complex autonomous driving scenarios. However, DRL models inevitably bring high memory consumption and computation, which hinders their wide deployment in resource-limited…

Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model…

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…

Many techniques have been developed, such as model compression, to make Deep Neural Networks (DNNs) inference more efficiently. Nevertheless, DNNs still lack excellent run-time dynamic inference capability to enable users trade-off accuracy…

Neural ranking models for information retrieval (IR) use shallow or deep neural networks to rank search results in response to a query. Traditional learning to rank models employ machine learning techniques over hand-crafted IR features. By…

Recent research on deep neural networks (DNNs) has primarily focused on improving the model accuracy. Given a proper deep learning framework, it is generally possible to increase the depth or layer width to achieve a higher level of…

Huge embedding tables in modern deep learning recommender models (DLRM) require prohibitively large memory during training and inference. This paper proposes FIITED, a system to automatically reduce the memory footprint via FIne-grained…

Recommender systems present a customized list of items based upon user or item characteristics with the objective of reducing a large number of possible choices to a smaller ranked set most likely to appeal to the user. A variety of…

Deep Neural Networks (DNNs) have been a large driver for AI breakthroughs in recent years. However, these models have been getting increasingly large as they become more accurate and safe. This means that their training becomes increasingly…

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional fields, yet they face a critical fidelity-speed dilemma: deep…

Tabular data is a common format for storing information in rows and columns to represent data entries and their features. Although deep neural networks have become the main approach for modeling a wide range of domains including computer…