Understanding and Visualizing Data Iteration in Machine Learning

Hohman, Fred; Wongsuphasawat, Kanit; Kery, Mary Beth; Patel, Kayur

doi:10.1145/3313831.3376177

Cited by 87 publications

(46 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another relevant aspect for algorithmic accountability and transparency is how and from where input data are collected. As recently discussed by Hohman et al (Hohman et al, 2020), machine learning applications require an iterative process to create successful models (Amershi et al, 2014). In particular, Hohman et al (Hohman et al, 2020) have shown that data iteration (e.g.…”

Section: Algorithmic Transparency and Accountabilitymentioning

confidence: 99%

“…As recently discussed by Hohman et al (Hohman et al, 2020), machine learning applications require an iterative process to create successful models (Amershi et al, 2014). In particular, Hohman et al (Hohman et al, 2020) have shown that data iteration (e.g. collecting novel training data to improve model's performance) is equally important as model iteration (e.g.…”

Section: Algorithmic Transparency and Accountabilitymentioning

confidence: 99%

See 1 more Smart Citation

Ethical machines: The human-centric use of artificial intelligence

2021

View full text Add to dashboard Cite

Today's increased availability of large amounts of human behavioral data and advances in artificial intelligence (AI) are contributing to a growing reliance on algorithms to make consequential decisions for humans, including those related to access to credit or medical treatments, hiring, etc. Algorithmic decision-making processes might lead to more objective decisions than those made by humans who may be influenced by prejudice, conflicts of interest, or fatigue. However, algorithmic decision-making has been criticized for its potential to lead to privacy invasion, information asymmetry, opacity, and discrimination. In this paper, we describe available technical solutions in three large areas that we consider to be of critical importance to achieve a human-centric AI: (1) privacy and data ownership; (2) accountability and transparency; and (3) fairness. We also highlight the criticality and urgency to engage multi-disciplinary teams of researchers, practitioners, policy makers, and citizens to co-develop and evaluate in the real-world algorithmic decision-making processes designed to maximize fairness, accountability, and transparency while respecting privacy.

show abstract

Section: Algorithmic Transparency and Accountabilitymentioning

confidence: 99%

Section: Algorithmic Transparency and Accountabilitymentioning

confidence: 99%

Ethical machines: The human-centric use of artificial intelligence

2021

View full text Add to dashboard Cite

show abstract

“…Nowadays, the uses of massive amounts of data are rapidly increasing in many applications. The analysis of these data are grimy, irreconcilable and complex [44]. As a result vast amounts of time and money are often lost.…”

Section: Introductionmentioning

confidence: 99%

“…Several existing surveys partially touch the surface of our area of interest such as visualization contributes to a better understanding of DL [149], visualization of DL in computer vision [112], visualization for better understaning of ML models [81]; the state-of-theart predictive VA [82]; interactive machine learning [108]; interpretable ML [74]; and surveys of multidimensional visualization techniques [80,120]. Similar to our focus, a survey on VA for DL is presented by Hohman et al [44]. The following are the main points of their survey: (1) why should various aspects of a DL model be visualised?, (2) who uses DL visualisation?, (3) what to visualise in DL?, (4) how to visualise DL?, and (5) when will the visualisation phase take place during the process of developing and training a network?…”

Section: Introductionmentioning

confidence: 99%

Deep Visual Analytics (DVA): Applications, Challenges and Future Directions

Islam¹,

Akter²,

Ratan³

et al. 2021

HCIS

View full text Add to dashboard Cite

Visual interactive system (VIS) has been received significant attention for solving various complex problems. However, designing and implementing a novel VIS with the large scale of data is a challenging task. While existing studies have applied various visual analytics (VA) to analyze and visualize insightful information, deep visual analytics (DVA) have considered as a promising technique to provide input evidences and explain system results. In this study, we present several deep learning (DL) techniques for analyzing data with visualization, which summarizes the state-of-the-art review on (i) big data analysis, (ii) cognitive and perception science, (iii) customer behavior analysis, (iv) natural language processing, (v) recommended system, (vi) healthcare analysis, (vii) fintech ecosystem, and (viii) tourism management. We present open research challenges for emerging DVA in the visualization community. We also highlight some key themes from the existing literature that may help to explore for future study. Thus, our goal is to help readers and researchers in DL and VA to understand key aspects in designing VIS for analysing data.

show abstract

“…A researcher may be interested in understanding trends in posts or images on social media. Here, summary statistics offer interpretable comparisons: we can plot the mean and standard deviation of a given marginal quantity over time, and easily see how it changes [19,20]. By contrast, coresets are harder to compare, since the exemplars selected for two datasets X 1 and X 2 will not in general overlap.…”

Section: Introductionmentioning

confidence: 99%

Understanding Collections of Related Datasets Using Dependent MMD Coresets

Williamson

Henderson²

2021

Information

View full text Add to dashboard Cite

Understanding how two datasets differ can help us determine whether one dataset under-represents certain sub-populations, and provides insights into how well models will generalize across datasets. Representative points selected by a maximum mean discrepancy (MMD) coreset can provide interpretable summaries of a single dataset, but are not easily compared across datasets. In this paper, we introduce dependent MMD coresets, a data summarization method for collections of datasets that facilitates comparison of distributions. We show that dependent MMD coresets are useful for understanding multiple related datasets and understanding model generalization between such datasets.

show abstract

Understanding and Visualizing Data Iteration in Machine Learning

Cited by 87 publications

References 31 publications

Ethical machines: The human-centric use of artificial intelligence

Ethical machines: The human-centric use of artificial intelligence

Deep Visual Analytics (DVA): Applications, Challenges and Future Directions

Understanding Collections of Related Datasets Using Dependent MMD Coresets

Contact Info

Product

Resources

About