Weaknesses: The term'unified' should be revised as the paper addresses a partial unification. For instance, the unified framework does not take into account a closed loop between the DNN and the explanation method (the explanation method can be itself another DNN interacting in a double sense with the prediction DNN) or other two-stage adaptive networks [1], [2]. In addition, an alternative to example based explanation is'opening the black box' in terms of intra-layer and inter-layer statistical properties of a DNN [3]: these may be enough to explain lack of generality (and thus absence of recommendation) of a given network depending on the input available data and the classification paradigm considered. Thus, a positioning must be provided with respect to the above issues in order to make the paper more informative with respect to the literature. The weak spots of the analysis are twofold.

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model, termed SparXnet, is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being a linear combination of rescaled versions of these features. We demonstrate the ability to select significant features while maintaining comparable predictive performance and direct interpretability through extensive experiments on synthetic and real-world datasets. We also provide theoretical analysis on the generalization bounds of our framework, which is favorably linear in the number of selected features and only logarithmic in the number of input features. We further lift any dependence of sample complexity on the number of parameters or the architectural details under very mild conditions. Our research paves the way for further research on sparse and explainable neural networks with guarantee.

"As far as AI in banking is concerned, explainability and fairness will be must-haves in 2-3 years because bill C-27 and OSFI expectations are going to require them." Ahead of the RE•WORK - Toronto AI Summit, we asked Eric Lanoix, Vice President, Quantitative Risk at Coast Capital Savings his thoughts on the topic. Here's what he had to say: What do you think is the most important advancement for AI in Finance? What are some recent wins from an AI project you are working on? What challenges did you face during it?

Machine Learning algorithms are increasingly being used in recent years due to their flexibility in model fitting and increased predictive performance. However, the complexity of the models makes them hard for the data analyst to interpret the results and explain them without additional tools. This has led to much research in developing various approaches to understand the model behavior. In this paper, we present the Explainable Neural Network (xNN), a structured neural network designed especially to learn interpretable features. Unlike fully connected neural networks, the features engineered by the xNN can be extracted from the network in a relatively straightforward manner and the results displayed. With appropriate regularization, the xNN provides a parsimonious explanation of the relationship between the features and the output. We illustrate this interpretable feature--engineering property on simulated examples.