We propose an approach for early crop classification through identifying
important timesteps with eXplainable AI (XAI) methods. Our approach consists of
training a baseline crop classification model to carry out layer-wise relevance
propagation (LRP) so that the salient time step can be identified. We chose a
selected number of such important time indices to create the bounding region of
the shortest possible classification timeframe. We identified the period 21st
April 2019 to 9th August 2019 as having the best trade-off in terms of accuracy
and earliness. This timeframe only suffers a 0.75% loss in accuracy as compared
to using the full timeseries. We observed that the LRP-derived important
timesteps also highlight small details in input values that differentiates
between different classes and

我们提出一种通过使用可解释的人工智能（XAI）方法来提前进行作物分类的方法。我们的方法包括训练一个基准作物分类模型，以进行层内相关传播（LRP），从而可以确定显著的时间步长。我们选择了一些重要的时间索引来创建可能的最短分类时间范围。我们确定了 2019 年 4 月 21 日至 2019 年 8 月 9 日的这段时间在准确性和提前性方面有着最佳平衡。与使用完整时间序列相比，这个时间范围仅损失了 0.75% 的准确性。我们观察到基于 LRP 得到的重要时间步长还突出了区分不同类别的输入值中的细小细节。

早期作物分类的可解释人工智能 (XAI)

XAI for Early Crop Classification

A linear multi-factor model is one of the most important tools in equity
portfolio management. The linear multi-factor models are widely used because
they can be easily interpreted. However, financial markets are not linear and
their accuracy is limited. Recently, deep learning methods were proposed to
predict stock return in terms of the multi-factor model. Although these methods
perform quite well, they have significant disadvantages such as a lack of
transparency and limitations in the interpretability of the prediction. It is
thus difficult for institutional investors to use black-box-type machine
learning techniques in actual investment practice because they should show
accountability to their customers. Consequently, the solution we propose is
based on LSTM with LRP. Specifically, we extend the linear multi-factor model
to be non-linear and time-varying with LSTM. Then, we approximate and linearize
the learned LSTM models by LRP. We call this LSTM+LRP model a deep recurrent
factor model. Finally, we perform an empirical analysis of the Japanese stock
market and show that our recurrent model has better predictive capability than
the traditional linear model and fully-connected deep learning methods.

该研究中提出了一种基于 LSTM 和 LRP 的深度复发因子模型，将线性多因子模型扩展为非线性和时变，具有更好的预测能力。

深度循环因子模型：可解释的非线性和时变多因子模型

Deep Recurrent Factor Model: Interpretable Non-Linear and Time-Varying  Multi-Factor Model

DeConvNet, Guided BackProp, LRP, were invented to better understand deep
neural networks. We show that these methods do not produce the theoretically
correct explanation for a linear model. Yet they are used on multi-layer
networks with millions of parameters. This is a cause for concern since linear
models are simple neural networks. We argue that explanation methods for neural
nets should work reliably in the limit of simplicity, the linear models. Based
on our analysis of linear models we propose a generalization that yields two
explanation techniques (PatternNet and PatternAttribution) that are
theoretically sound for linear models and produce improved explanations for
deep networks.

通过分析线性模型，我们提出了两种更可靠、理论上更加准确的解释方法（PatternNet 和 PatternAttribution），适用于线性模型，并可改善深度神经网络的解释。

学习解释神经网络：PatternNet 与 PatternAttribution

Learning how to explain neural networks: PatternNet and  PatternAttribution

Layer-wise relevance propagation (LRP) is a recently proposed technique for
explaining predictions of complex non-linear classifiers in terms of input
variables. In this paper, we apply LRP for the first time to natural language
processing (NLP). More precisely, we use it to explain the predictions of a
convolutional neural network (CNN) trained on a topic categorization task. Our
analysis highlights which words are relevant for a specific prediction of the
CNN. We compare our technique to standard sensitivity analysis, both
qualitatively and quantitatively, using a "word deleting" perturbation
experiment, a PCA analysis, and various visualizations. All experiments
validate the suitability of LRP for explaining the CNN predictions, which is
also in line with results reported in recent image classification studies.

本研究使用层内重要性传播技术（LRP）首次探究其在自然语言处理（NLP）中的应用，特别是用于解释卷积神经网络（CNN）在主题分类任务中的预测结果，并通过多项实验验证 LRP 方法解释 CNN 预测的适用性，实验结果于最近的图像分类研究结果相符。