In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.

https://dl.acm.org/doi/pdf/10.1145/3236009

A Survey of Methods for Explaining Black Box Models

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such as safety or non-discrimination. However, despite the interest in interpretability, there is very little consensus on what interpretable machine learning is and how it should be measured. In this position paper, we first define interpretability and describe when interpretability is needed (and when it is not). Next, we suggest a taxonomy for rigorous evaluation and expose open questions towards a more rigorous science of interpretable machine learning.

Towards A Rigorous Science of Interpretable Machine Learning

Newness and distinctiveness is claimed in the features of ornamentation as shown inside the broken line circle in the accompanying representation.

Display screen or portion thereof with graphical user interface

A surgical instrument can comprise a channel configured to support a staple cartridge and, in addition, an anvil pivotable between open and closed positions relative to the channel. The surgical instrument can further comprise a cutting member configured to incise tissue positioned captured between the staple cartridge and the anvil and, in addition, means for stopping the cutting member prior to a distal end datum, wherein the distal end datum can be defined by the distal-most staple cavity in the staple cartridge. In such embodiments, the incision within the tissue may not extend beyond the portion of the tissue that has been stapled.

Surgical stapling instrument with an articulatable end effector

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

A system and method of controlling a vehicle with a trailer comprises determining the presence of a trailer, generating an oscillation signal indicative of trailer swaying relative to the vehicle, generating an initial weighted dynamic control signal for a vehicle dynamic control system in response to the oscillation signal, operating at least one vehicle dynamic system according to the dynamic control signal, and thereafter, iteratively generating a penalty function for the weighted dynamic control signal as a function of the oscillation signal response. A neural network with an associated trainer modifies the dynamic control signal as a function of trailer sway response.

Trailer Oscillation Detection and Compensation Method For A Vehicle And Trailer Combination

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 they produce a set of rules that concisely describe a specific class. We present two probabilistic models with prior parameters that the user can set to encourage the model to have a desired size and shape, to conform with a domain-specific definition of interpretability. We provide a scalable MAP inference approach and develop theoretical bounds to reduce computation by iteratively pruning the search space. We apply our method (Bayesian Rule Sets - BRS) to characterize and predict user behavior with respect to in-vehicle context-aware personalized recommender systems. Our method has a major advantage over classical associative classification methods and decision trees in that it does not greedily grow the model.

/pdf/a-bayesian-framework-for-learning-rule-sets-for-5eycxmg6ct.pdf

A Bayesian framework for learning rule sets for interpretable classification

One or more embodiments may include a trip planning system for planning a trip based on the charge of an electric vehicle battery. The trip planning system may include one or more computers located remotely from an electric vehicle which may have one or more battery packs for powering the electric vehicle. The computer(s) may be configured to receive geographic parameters defining a trip and a battery charge status of the one or more electric vehicle battery packs. The computer(s) may be further configured to determine that the trip cannot be completed based on the battery charge status. The computer(s) may additionally be configured to present a battery charge requirement for completing the trip.

Method and system for monitoring an energy storage system for a vehicle for trip planning

Information about a device may be emotively conveyed to a user of the device. Input indicative of an operating state of the device may be received. The input may be transformed into data representing a simulated emotional state. Data representing an avatar that expresses the simulated emotional state may be generated and displayed. A query from the user regarding the simulated emotional state expressed by the avatar may be received. The query may be responded to.

Emotive advisory system and method

A method of intelligent music selection in a vehicle includes learning user preferences for music selection in the vehicle corresponding to a plurality of driving conditions of the vehicle. Input is received that is indicative of a current driving condition of the vehicle. And, music is selected and played based on the learned user preferences for music selection in the vehicle corresponding to the current driving condition.

Perry Robinson MacNeille

Papers

Trailer Oscillation Detection and Compensation Method For A Vehicle And Trailer Combination

A Bayesian framework for learning rule sets for interpretable classification

Method and system for monitoring an energy storage system for a vehicle for trip planning

Emotive advisory system and method

Intelligent music selection in vehicles