Related papers: iNNspector: Visual, Interactive Deep Model Debuggi…

Inherent limitations of contemporary machine learning systems in crucial areas -- importantly in continual learning, information reuse, comprehensibility, and integration with deliberate behavior -- are receiving increasing attention. To…

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an…

When engineers train deep learning models, they are very much 'flying blind'. Commonly used methods for real-time training diagnostics, such as monitoring the train/test loss, are limited. Assessing a network's training process solely…

Debugging is an essential part of software maintenance and evolution since it allows software developers to analyze program execution step by step. Understanding a program is required to fix potential flaws, alleviate bottlenecks, and…

Interpretation and diagnosis of machine learning models have gained renewed interest in recent years with breakthroughs in new approaches. We present Manifold, a framework that utilizes visual analysis techniques to support interpretation,…

In the modern world, we are permanently using, leveraging, interacting with, and relying upon systems of ever higher sophistication, ranging from our cars, recommender systems in e-commerce, and networks when we go online, to integrated…

Many researchers have studied the behaviour of successful developers while debugging desktop software. In this paper, we investigate the embedded-software debugging by intermediate programmers through an exploratory study. The bugs are…

Researchers have been highly active to investigate the classical machine learning workflow and integrate best practices from the software engineering lifecycle. However, deep learning exhibits deviations that are not yet covered in this…

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…

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated…

Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…

We develop a two-stage deep learning framework that recommends fashion images based on other input images of similar style. For that purpose, a neural network classifier is used as a data-driven, visually-aware feature extractor. The latter…

Providing effective feedback for programming assignments in computer science education can be challenging: students solve problems by iteratively submitting code, executing it, and using limited feedback from the compiler or the auto-grader…

Deep reinforcement learning (DRL) has attracted much attention in automated game testing. Early attempts rely on game internal information for game space exploration, thus requiring deep integration with games, which is inconvenient for…

Encoding and decoding models are widely used in systems, cognitive, and computational neuroscience to make sense of brain-activity data. However, the interpretation of their results requires care. Decoding models can help reveal whether…

Despite their success and widespread adoption, the opaque nature of deep neural networks (DNNs) continues to hinder trust, especially in critical applications. Current interpretability solutions often yield inconsistent or oversimplified…

Data programming is a programmatic weak supervision approach to efficiently curate large-scale labeled training data. Writing data programs (labeling functions) requires, however, both programming literacy and domain expertise. Many subject…

High-level shape understanding and technique evaluation on large repositories of 3D shapes often benefit from additional information known about the shapes. One example of such information is the semantic segmentation of a shape into…

While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime…

The increasing use of complex machine learning models in education has led to concerns about their interpretability, which in turn has spurred interest in developing explainability techniques that are both faithful to the model's inner…