Steering deep sequence model with prototypes

Abstract

A deep sequence model with prototypes may be steered. A prototype overview is displayed, the prototype overview including a plurality of prototype sequences learned by a model through backpropagation, each of the prototype sequences including a series of events, wherein for each of the prototype sequences, statistical information is presented with respect to use of the prototype sequence by the model. Input is received adjusting one or more of the prototype sequences to fine-tune the model. The model is updated using the plurality of prototype sequences, as adjusted, to create an updated model. The model, as updated, is displayed in the prototype overview.

Description

technical field [0001] The present disclosure relates to utilizing prototypes to manipulate deep sequence models. Background technique [0002] Deep learning models are employed in sequence data analysis to aid in decision making. Deep sequence models such as recurrent neural networks (RNNs) can be used to predict patient states by modeling electronic health records (EHRs), analyzing the topic or sentiment of text, and understanding audio signals. Such techniques have achieved state-of-the-art results in various applications. [0003] Despite their excellent performance, RNNs are often viewed as "black boxes". This is due to its complex architecture as well as the huge size of the model weights. This lack of interpretability limits the adoption of RNNs in many critical decision-making scenarios, where understanding of the reasons behind predictions may be required. As an example, the EU's recent data protection regulations grant individuals a "right to interpretation" ov...

AI Technical Summary

Problems solved by technology

Although end-to-end training of deep neural networks can alleviate the need to manually manage data features, training alone cannot provide expert users with the functionality to manipulate the model

Images