This discussion paper reviews both finance and computer science literature on sentiment.
The toolset for addressing the sentiment analysis problem in computer science goes beyond …

It is said that beauty is in the eye of the beholder. But how exactly can we characterize such
discrepancies in interpretation? For example, are there any specific features of an image …

We demonstrate a network visualization technique to analyze the recurrent state inside the
LSTMs/GRUs used commonly in language and acoustic models. Interpreting intermediate …

In learning a predictive model over multivariate time series consisting of target and
exogenous variables, the forecasting performance and interpretability of the model are both …

Recurrent neural networks (RNNs) are an effective representation of control policies for a
wide range of reinforcement learning problems. RNN policies, however, are particularly …

This paper demonstrates that machine learning techniques can be used to efficiently
forecast macroeconomic time series. We show that artificial neural networks outperform a …

Surface ozone can trigger many health problems for human (eg coughing, bronchitis,
emphysema, and asthma), especially for children and the elderly. It also has harmful effects …

We propose nonlinearized relevance propagation (NRP), an improved method of exploring
deep neural networks (DNN). This method derives from well-known layer-wise relevance …

In this thesis, attribution-based explanation approaches on text classification problem with
TextCNN is investigated. Two explanation approaches were investigated: Layer-wise …

It is said that beauty is in the eye of the beholder. But how exactly can we characterize such
discrepancies in interpretation? For example, are there any specific features of an image …