Interpretability of deep learning models: A survey of results

Chakraborty, Supriyo; Tomsett, Richard; Raghavendra, Ramya; Harborne, Daniel; Alzantot, Moustafa; Cerutti, Federico; Srivastava, Mani; Preece, Alun; Julier, Simon; Rao, Raghuveer M.; Kelley, Troy D.; Braines, Dave; Şensoy, Murat; Willis, Christopher J.; Gurram, Prudhvi

doi:10.1109/uic-atc.2017.8397411

Cited by 262 publications

(195 citation statements)

References 28 publications

Supporting

Mentioning

189

Contrasting

Unclassified

Order By: Relevance

“…This lack of interpretability has been widely regarded as a major reason impeding the pervasive application of DRL in the networking industry, albeit this is true in general with regard to its application in other domains as well. Active research has been undertaken to address this limitation and facilitate a better interpretability of learning algorithms [41].…”

Section: Discussion Of Results and Future Researchmentioning

confidence: 99%

Optimizing Throughput Performance in Distributed MIMO Wi-Fi Networks Using Deep Reinforcement Learning

Kumarappan

Torkildson

Mandayam

et al. 2020

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

This paper explores the feasibility of leveraging concepts from deep reinforcement learning (DRL) to enable dynamic resource management in Wi-Fi networks implementing distributed multi-user MIMO (D-MIMO). D-MIMO is a technique by which a set of wireless access points are synchronized and grouped together to jointly serve multiple users simultaneously. This paper addresses two dynamic resource management problems pertaining to D-MIMO Wi-Fi networks: (i) channel assignment of D-MIMO groups, and (ii) deciding how to cluster access points to form D-MIMO groups, in order to maximize user throughput performance. These problems are known to be NP-Hard and only heuristic solutions exist in literature. We construct a DRL framework through which a learning agent interacts with a D-MIMO Wi-Fi network, learns about the network environment, and is successful in converging to policies which address the aforementioned problems. Through extensive simulations and on-line training based on D-MIMO Wi-Fi networks, this paper demonstrates the efficacy of DRL in achieving an improvement of 20% in user throughput performance compared to heuristic solutions, particularly when network conditions are dynamic. This work also showcases the effectiveness of DRL in meeting multiple network objectives simultaneously, for instance, maximizing throughput of users as well as fairness of throughput among them.

show abstract

Section: Discussion Of Results and Future Researchmentioning

confidence: 99%

Optimizing Throughput Performance in Distributed MIMO Wi-Fi Networks Using Deep Reinforcement Learning

Kumarappan

Torkildson

Mandayam

et al. 2020

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…Because we employed transfer learning, the features that were extracted were based on the ImageNet classification task, and it is unclear how these features related to MRI-specific artifacts. However, interpretability of deep learning is an ongoing active field of research (Chakraborty et al, 2017), and we may be able to fit more interpretable models in the future.…”

Section: Limitationsmentioning

confidence: 99%

Combining citizen science and deep learning to amplify expertise in neuroimaging

Keshavan

Yeatman

Rokem

2018

Preprint

View full text Add to dashboard Cite

Research in many fields has become increasingly reliant on large and complex datasets. "Big Data" holds untold promise to rapidly advance science by tackling new questions that cannot be answered with smaller datasets. While powerful, research with Big Data poses unique challenges, as many standard lab protocols rely on experts examining each one of the samples. This is not feasible for large-scale datasets because manual approaches are time-consuming and hence difficult to scale. Meanwhile, automated approaches lack the accuracy of examination by highly trained scientists and this may introduce major errors, sources of noise, and unforeseen biases into these large and complex datasets. Our proposed solution is to 1) start with a small, expertly labelled dataset, 2) amplify labels through web-based tools that engage citizen scientists, and 3) train machine learning on amplified labels to emulate expert decision making. As a proof of concept, we developed a system to quality control a large dataset of three-dimensional magnetic resonance images (MRI) of human brains. An initial dataset of 200 brain images labeled by experts were amplified by citizen scientists to label 722 brains, with over 80,000 ratings done through a simple web interface. A deep learning algorithm was then trained to predict data quality, based on a combination of the citizen scientist labels that accounts for differences in the quality of classification by different citizen scientists. In an ROC analysis (on left out test data), the deep learning network performed as well as a state-of-the-art, specialized algorithm (MRIQC) for quality control of T1-weighted images, each with an area under the curve of 0.99. Finally, as a specific practical application of the method, we explore how brain image quality relates to the replicability of a well established relationship between brain volume and age over development. Combining citizen science and deep learning can generalize and scale expert decision making; this is particularly important in emerging disciplines where specialized, automated tools do not already exist.

show abstract

“…However, the effectiveness of supervised training relies heavily on data quantity and label quality, especially in data with a wide range of data-specific factors of variations. Moreover, interpreting the results of these networks -important in areas such as clinical tasks -remains challenging [1].…”

Section: Introductionmentioning

confidence: 99%

Improving Disentangled Representation Learning with the Beta Bernoulli Process

Gyawali

Knight

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

View full text Add to dashboard Cite

To improve the ability of variational auto-encoders (VAE) to disentangle in the latent space, existing works mostly focus on enforcing the independence among the learned latent factors. However, the ability of these models to disentangle often decreases as the complexity of the generative factors increases. In this paper, we investigate the little-explored effect of the modeling capacity of a posterior density on the disentangling ability of the VAE. We note that the independence within and the complexity of the latent density are two different properties we constrain when regularizing the posterior density: while the former promotes the disentangling ability of VAE, the latter -if overly limitedcreates an unnecessary competition with the data reconstruction objective in VAE. Therefore, if we preserve the independence but allow richer modeling capacity in the posterior density, we will lift this competition and thereby allow improved independence and data reconstruction at the same time. We investigate this theoretical intuition with a VAE that utilizes a non-parametric latent factor model, the Indian Buffet Process (IBP), as a latent density that is able to grow with the complexity of the data. Across three widely-used benchmark data sets (MNIST, 3D Chairs and dSprites) and two clinical data sets little explored for disentangled learning, we qualitatively and quantitatively demonstrated the improved disentangling performance of IBP-VAE over the state of the art. In the latter two clinical data sets riddled with complex factors of variations, we further demonstrated that unsupervised disentangling of nuisance factors via IBP-VAE -when combined with a supervised objective -can not only improve task accuracy in comparison to relevant supervised deep architectures, but also facilitate knowledge discovery related to task decision-making. A shorter version of this work will appear in the ICDM 2019 conference proceedings.

show abstract

Interpretability of deep learning models: A survey of results

Cited by 262 publications

References 28 publications

Optimizing Throughput Performance in Distributed MIMO Wi-Fi Networks Using Deep Reinforcement Learning

Optimizing Throughput Performance in Distributed MIMO Wi-Fi Networks Using Deep Reinforcement Learning

Combining citizen science and deep learning to amplify expertise in neuroimaging

Improving Disentangled Representation Learning with the Beta Bernoulli Process

Contact Info

Product

Resources

About