Related papers: Cockpit: A Practical Debugging Tool for the Traini…

The future success of the Navy will depend, in part, on artificial intelligence. In practice, many artificially intelligent algorithms, and in particular deep learning models, rely on continual learning to maintain performance in dynamic…

Monitoring the inner state of deep neural networks is essential for auditing the learning process and enabling timely interventions. While conventional metrics like validation loss offer a surface-level view of performance, the evolution of…

Compared with traditional seismic noise attenuation algorithms that depend on signal models and their corresponding prior assumptions, removing noise with a deep neural network is trained based on a large training set, where the inputs are…

From computer vision and speech recognition to forecasting trajectories in autonomous vehicles, deep learning approaches are at the forefront of so many domains. Deep learning models are developed using plethora of high-level, generic…

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the…

Data debugging is to find a subset of the training data such that the model obtained by retraining on the subset has a better accuracy. A bunch of heuristic approaches are proposed, however, none of them are guaranteed to solve this problem…

We introduce an open-source toolkit, i.e., the deep Self End-to-end Learning Framework (deepSELF), as a toolkit of deep self end-to-end learning framework for multi-modal signals. To the best of our knowledge, it is the first public toolkit…

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

Deep learning models in recommender systems are usually trained in the batch mode, namely iteratively trained on a fixed-size window of training data. Such batch mode training of deep learning models suffers from low training efficiency,…

Software development in the aerospace domain requires adhering to strict, high-quality standards. While there exist regulatory guidelines for commercial software in this domain (e.g., ARP-4754 and DO-178), these do not apply to software…

Motion blur in videos captured by autonomous vehicles and robots can degrade their perception capability. In this work, we present a novel approach to video deblurring by fitting a deep network to the test video. Our key observation is that…

Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases there is value in training a network just from the input at hand. This is particularly relevant in many signal and image…

In post-silicon validation, tuning is to find the values for the tuning knobs, potentially as a function of process parameters and/or known operating conditions. In this sense, an more efficient tuning requires identifying the most critical…

As new deep-learned error-correcting codes continue to be introduced, it is important to develop tools to interpret the designed codes and understand the training process. Prior work focusing on the deep-learned TurboAE has both interpreted…

Third-party resources ($e.g.$, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a new training-phase threat. In general, backdoor attackers…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…

Many real-world time-series analysis problems are characterised by scarce data. Solutions typically rely on hand-crafted features extracted from the time or frequency domain allied with classification or regression engines which condition…

As the potential for neural networks to augment our daily lives grows, ensuring their quality through effective testing, debugging, and maintenance is essential. This is especially the case as we acknowledge the prospects of negative…

Data-driven control in unknown environments requires a clear understanding of the involved uncertainties for ensuring safety and efficient exploration. While aleatoric uncertainty that arises from measurement noise can often be explicitly…

The coin-tap test is a convenient and primary method for non-destructive testing, while its manual on-site operation is tough and costly. With the help of the latest intelligent signal processing method, convolutional neural networks (CNN),…