Interpretable Sequence Classification via Discrete Optimization

Abstract

Sequence classification is the task of predicting a class label given a sequence of observations. In many applications such as healthcare monitoring or intrusion detection, early classification is crucial to prompt intervention. In this work, we learn sequence classifiers that favour early classification from an evolving observation trace. While many state-of-the-art sequence classifiers are neural networks, and in particular LSTMs, our classifiers take the form of finite state automata and are learned via discrete optimization. Our automata-based classifiers are interpretable---supporting explanation, counterfactual reasoning, and human-in-the-loop modification---and have strong empirical performance. Experiments over a suite of goal recognition and behaviour classification datasets show our learned automata-based classifiers to have comparable test performance to LSTM-based classifiers, with the added advantage of being interpretable.

Model Discrimination of Switched Nonlinear Systems With Temporal Logic-Constrained Switching

“…For the purpose of distinguishing amongst different model behaviors, we can leverage the differences that are the result of different system dynamics or specifications, where the system dynamics governs the evolution of system states based on physical laws and the specification governs the temporal evolution of their system modes corresponding to desired tasks or rules. The task specifications are often expressed using temporal logic formulas, such as linear temporal logic (LTL) formulas, which is a highly expressive language capable of providing formal yet easily understandable descriptions of system behaviors [1], [2]. Temporal logic formulas are widely used across many fields, including control synthesis and complex robotic applications, anomaly detection in underlying systems, and specification, recognition, and interpretation in dynamic environments [3]- [11].…”