[HTML][HTML] Methods for interpreting and understanding deep neural networks
This paper provides an entry point to the problem of interpreting a deep neural network
model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. As a …
model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. As a …
Explainable sentiment analysis with applications in medicine
Sentiment Analysis can help to extract knowledge related to opinions and emotions from
user generated text information. It can be applied in medical field for patients monitoring …
user generated text information. It can be applied in medical field for patients monitoring …
[PDF][PDF] Interpreting and explaining deep neural networks for classification of audio signals
Interpretability of deep neural networks is a recently emerging area of machine learning
research targeting a better understanding of how models perform feature selection and …
research targeting a better understanding of how models perform feature selection and …
Extracting automata from recurrent neural networks using queries and counterexamples
We present a novel algorithm that uses exact learning and abstraction to extract a
deterministic finite automaton describing the state dynamics of a given trained RNN. We do …
deterministic finite automaton describing the state dynamics of a given trained RNN. We do …
Evaluating neural network explanation methods using hybrid documents and morphological agreement
The behavior of deep neural networks (DNNs) is hard to understand. This makes it
necessary to explore post hoc explanation methods. We conduct the first comprehensive …
necessary to explore post hoc explanation methods. We conduct the first comprehensive …
Interpreting recurrent and attention-based neural models: a case study on natural language inference
Deep learning models have achieved remarkable success in natural language inference
(NLI) tasks. While these models are widely explored, they are hard to interpret and it is often …
(NLI) tasks. While these models are widely explored, they are hard to interpret and it is often …
Explaining therapy predictions with layer-wise relevance propagation in neural networks
In typical data analysis projects in biology and healthcare, simpler predictive models, such
as regressions and decision trees, enjoy more popularity than more complex and expressive …
as regressions and decision trees, enjoy more popularity than more complex and expressive …
Learning finite state representations of recurrent policy networks
Recurrent neural networks (RNNs) are an effective representation of control policies for a
wide range of reinforcement and imitation learning problems. RNN policies, however, are …
wide range of reinforcement and imitation learning problems. RNN policies, however, are …
Before name-calling: Dynamics and triggers of ad hominem fallacies in web argumentation
Arguing without committing a fallacy is one of the main requirements of an ideal debate. But
even when debating rules are strictly enforced and fallacious arguments punished, arguers …
even when debating rules are strictly enforced and fallacious arguments punished, arguers …
Extractive adversarial networks: High-recall explanations for identifying personal attacks in social media posts
We introduce an adversarial method for producing high-recall explanations of neural text
classifier decisions. Building on an existing architecture for extractive explanations via hard …
classifier decisions. Building on an existing architecture for extractive explanations via hard …