Bayesian deep learning: A model-based interpretable approach

Melanoma detection with a deep learning model

Background: Skin cancer is one of the most common forms of cancer in the world and melanoma is the deadliest type of skin cancer. Both melanoma and melanocytic nevi begin in melanocytes (cells that produce melanin). However, melanocytic nevi are benign whereas melanoma is malignant. This work proposes a deep learning model for classification of these two lesions.    Methods: In this analytic s...

InterpNET: Neural Introspection for Interpretable Deep Learning

Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological evidence of the human visual system’s inner-workings. This paper proposes a neural network design paradigm, termed InterpNET, which can be combined with any...

A Bayesian Data Augmentation Approach for Learning Deep Models

Data augmentation is an essential part of the training process applied to deep learning models. The motivation is that a robust training process for deep learning models depends on large annotated datasets, which are expensive to be acquired, stored and processed. Therefore a reasonable alternative is to be able to automatically generate new annotated training samples using a process known as d...

A Bayesian Framework for Learning Rule Sets for Interpretable Classification

We present a machine learning algorithm for building classifiers that are comprised of a small number of short rules. These are restricted disjunctive normal form models. An example of a classifier of this form is as follows: If X satisfies (condition A AND condition B) OR (condition C) OR · · · , then Y = 1. Models of this form have the advantage of being interpretable to human experts since t...

Bayesian Deep Learning | Uncertainty in Deep Learning