Search Results for author:
Found 6 papers, 3 papers with code
Benchmarking Deep Learning Interpretability in Time Series Predictions
Saliency methods are used extensively to highlight the importance of input features in model predictions.
Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks
In this work we analyze saliency-based methods for RNNs, both classical and gated cell architectures.
Improving Deep Learning Interpretability by Saliency Guided Training
In this paper, we tackle this issue and introduce a {\it saliency guided training}procedure for neural networks to reduce noisy gradients used in predictions while retaining the predictive performance of the model.
Improving Long-Horizon Forecasts with Expectation-Biased LSTM Networks
State-of-the-art forecasting methods using Recurrent Neural Net- works (RNN) based on Long-Short Term Memory (LSTM) cells have shown exceptional performance targeting short-horizon forecasts, e. g given a set of predictor features, forecast a target value for the next few time steps in the future.
Improving Multimodal Accuracy Through Modality Pre-training and Attention
Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance.
Interpretable Mixture of Experts
In addition to constituting a standalone inherently-interpretable architecture, IME has the premise of being integrated with existing DNNs to offer interpretability to a subset of samples while maintaining the accuracy of the DNNs.
