Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers

Hohman, Fred; Kahng, Minsuk; Pienta, Robert; Chau, Duen Horng

doi:10.1109/tvcg.2018.2843369

Cited by 449 publications

(321 citation statements)

References 105 publications

Supporting

Mentioning

320

Contrasting

Unclassified

Order By: Relevance

“…More broadly, our work relates to the literature on visual analysis of neural networks (see [HKPC18] for a survey). Previous work has contributed techniques and systems to visualize hidden layers [ZF14, LSL * 17], training process [LSC * 18, PHVG * 18], model architecture [WSW * 18] and supervised learning results [RAL * 17].…”

Section: Visualizing Latent Spacesmentioning

confidence: 99%

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Liu

Jun

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

Latent spaces—reduced‐dimensionality vector space embeddings of data, fit via machine learning—have been shown to capture interesting semantic properties and support data analysis and synthesis within a domain. Interpretation of latent spaces is challenging because prior knowledge, sometimes subtle and implicit, is essential to the process. We contribute methods for “latent space cartography”, the process of mapping and comparing meaningful semantic dimensions within latent spaces. We first perform a literature survey of relevant machine learning, natural language processing, and scientific research to distill common tasks and propose a workflow process. Next, we present an integrated visual analysis system for supporting this workflow, enabling users to discover, define, and verify meaningful relationships among data points, encoded within latent space dimensions. Three case studies demonstrate how users of our system can compare latent space variants in image generation, challenge existing findings on cancer transcriptomes, and assess a word embedding benchmark.

show abstract

Section: Visualizing Latent Spacesmentioning

confidence: 99%

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Liu

Jun

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…In the field of visual analytics, a number of methods have been developed to illustrate the working mechanism of a variety of DNNs, such as CNN [18], [19], [20], RNN [21], [22], [23], [24], deep generative models [25], [26], [27], and deep reinforcement learning models [28]. Hohman et al [29] presented a comprehensive survey to summarize the state-of-the-art visual analysis methods for explainable deep learning. Existing methods can be categorized into three classes: network-centric [30], [31], [32], instance-centric [20], [33], [34], [35], and hybrid [36], [37].…”

Section: Related Workmentioning

confidence: 99%

Analyzing the Noise Robustness of Deep Neural Networks

Cao

Liu

et al. 2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

A B C D E (a) Input images (b) Datapath visualization at the network-and layer-levels (c) Neuron visualization Figure 1: Explanation why an adversarial panda image is not classified as a panda. The root cause is identified as the neurons in the feature map F A failing to detect the outline of the panda's ear (E) in the adversarial example, which further leads to the failure of detecting the panda's ear (B) in F C1 . Abstract-Adversarial examples, generated by adding small but intentionally imperceptible perturbations to normal examples, can mislead deep neural networks (DNNs) to make incorrect predictions. Although much work has been done on both adversarial attack and defense, a fine-grained understanding of adversarial examples is still lacking. To address this issue, we present a visual analysis method to explain why adversarial examples are misclassified. The key is to compare and analyze the datapaths of both the adversarial and normal examples. A datapath is a group of critical neurons along with their connections. We formulate the datapath extraction as a subset selection problem and solve it by constructing and training a neural network. A multi-level visualization consisting of a network-level visualization of data flows, a layer-level visualization of feature maps, and a neuron-level visualization of learned features, has been designed to help investigate how datapaths of adversarial and normal examples diverge and merge in the prediction process. A quantitative evaluation and a case study were conducted to demonstrate the promise of our method to explain the misclassification of adversarial examples.

show abstract

“…[154] reviewed 381 papers on existing XAI approaches from interdisciplinary perspectives. As reported in [155], the scope of their SLR is visualization and visual analytics for deep learning. The study [155] focused on studies that adopted visual analytics to explaining neural network decisions.…”

Section: Slr Of Explainable Artificial Intelligence (Xai)mentioning

confidence: 99%

Testing and verification of neural-network-based safety-critical control software: A systematic literature review

Zhang

2020

Information and Software Technology

View full text Add to dashboard Cite

Context: Neural Network (NN) algorithms have been successfully adopted in a number of Safety-Critical Cyber-Physical Systems (SCCPSs). Testing and Verification (T&V) of NN-based control software in safety-critical domains are gaining interest and attention from both software engineering and safety engineering researchers and practitioners. Objective: With the increase in studies on the T&V of NN-based control software in safety-critical domains, it is important to systematically review the state-of-the-art T&V methodologies, to classify approaches and tools that are invented, and to identify challenges and gaps for future studies. Method: By searching the six most relevant digital libraries, we retrieved 950 papers on the T&V of NN-based Safety-Critical Control Software (SCCS). Then we filtered the papers based on the predefined inclusion and exclusion criteria and applied snowballing to identify new relevant papers. Results: To reach our result, we selected 83 primary papers published between 2001 and 2018, applied the thematic analysis approach for analyzing the data extracted from the selected papers, presented the classification of approaches, and identified challenges. Conclusion: The approaches were categorized into five high-order themes: assuring robustness of NNs, assuring safety properties of NN-based control software, improving the failure resilience of NNs, measuring and ensuring test completeness, and improving the interpretability of NNs. From the industry perspective, improving the interpretability of NNs is a crucial need in safetycritical applications. We also investigated nine safety integrity properties within four major safety lifecycle phases to investigate the achievement level of T&V goals in IEC 61508-3. Results show that correctness, completeness, freedom from intrinsic faults, and fault tolerance have drawn most attention from the research community. However, little effort has been invested in achieving repeatability; no reviewed study focused on precisely defined testing configuration or on defense against common cause failure.

show abstract

Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers

Cited by 449 publications

References 105 publications

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Latent Space Cartography: Visual Analysis of Vector Space Embeddings

Analyzing the Noise Robustness of Deep Neural Networks

Testing and verification of neural-network-based safety-critical control software: A systematic literature review

Contact Info

Product

Resources

About