Interpretability of deep learning models: a survey of results

Name: Interpretability of deep learning models: a survey of results
Author: Chakraborty, S., Tomsett, R., Raghavendra, R., Harborne, D., Alzantot, M., Cerutti, F., Srivastava, M., Preece, A., Julier, S., Rao, R. M., Kelley, T. D., Braines, D., Şensoy, Murat, Willis, C. J., Gurram, P.

İsim	Interpretability of deep learning models: a survey of results
Yazar	Chakraborty, S., Tomsett, R., Raghavendra, R., Harborne, D., Alzantot, M., Cerutti, F., Srivastava, M., Preece, A., Julier, S., Rao, R. M., Kelley, T. D., Braines, D., Şensoy, Murat, Willis, C. J., Gurram, P.
Basım Tarihi:	2018-06-26
Basım Yeri	- IEEE
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-1-5386-0435-9
Kayıt Numarası	5498f403-ca05-4a9d-92f2-60da905ae5b4
Lokasyon	Computer Science
Tarih	2018-06-26
Notlar	United States Department of Defense US Army Research Laboratory (ARL) ; UK Ministry of Defence
Örnek Metin	Deep neural networks have achieved near-human accuracy levels in various types of classification and prediction tasks including images, text, speech, and video data. However, the networks continue to be treated mostly as black-box function approximators, mapping a given input to a classification output. The next step in this human-machine evolutionary process - incorporating these networks into mission critical processes such as medical diagnosis, planning and control - requires a level of trust association with the machine output. Typically, statistical metrics are used to quantify the uncertainty of an output. However, the notion of trust also depends on the visibility that a human has into the working of the machine. In other words, the neural network should provide human-understandable justifications for its output leading to insights about the inner workings. We call such models as interpretable deep networks. Interpretability is not a monolithic notion. In fact, the subjectivity of an interpretation, due to different levels of human understanding, implies that there must be a multitude of dimensions that together constitute interpretability. In addition, the interpretation itself can be provided either in terms of the low-level network parameters, or in terms of input features used by the model. In this paper, we outline some of the dimensions that are useful for model interpretability, and categorize prior work along those dimensions. In the process, we perform a gap analysis of what needs to be done to improve model interpretability.
DOI	10.1109/UIC-ATC.2017.8397411

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Interpretability of deep learning models: a survey of results

Yazar Chakraborty, S., Tomsett, R., Raghavendra, R., Harborne, D., Alzantot, M., Cerutti, F., Srivastava, M., Preece, A., Julier, S., Rao, R. M., Kelley, T. D., Braines, D., Şensoy, Murat, Willis, C. J., Gurram, P.

Basım Tarihi 2018-06-26

Basım Yeri - IEEE

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-1-5386-0435-9

Kayıt Numarası 5498f403-ca05-4a9d-92f2-60da905ae5b4

Lokasyon Computer Science

Tarih 2018-06-26

Notlar United States Department of Defense US Army Research Laboratory (ARL) ; UK Ministry of Defence

Örnek Metin Deep neural networks have achieved near-human accuracy levels in various types of classification and prediction tasks including images, text, speech, and video data. However, the networks continue to be treated mostly as black-box function approximators, mapping a given input to a classification output. The next step in this human-machine evolutionary process - incorporating these networks into mission critical processes such as medical diagnosis, planning and control - requires a level of trust association with the machine output. Typically, statistical metrics are used to quantify the uncertainty of an output. However, the notion of trust also depends on the visibility that a human has into the working of the machine. In other words, the neural network should provide human-understandable justifications for its output leading to insights about the inner workings. We call such models as interpretable deep networks. Interpretability is not a monolithic notion. In fact, the subjectivity of an interpretation, due to different levels of human understanding, implies that there must be a multitude of dimensions that together constitute interpretability. In addition, the interpretation itself can be provided either in terms of the low-level network parameters, or in terms of input features used by the model. In this paper, we outline some of the dimensions that are useful for model interpretability, and categorize prior work along those dimensions. In the process, we perform a gap analysis of what needs to be done to improve model interpretability.

DOI 10.1109/UIC-ATC.2017.8397411