Search Results for author:
Found 14 papers, 4 papers with code
On The Potential of The Fractal Geometry and The CNNs Ability to Encode it
In this work, we investigate the features that are learned by deep models and we study whether these deep networks are able to encode features as complex and high-level as the fractal dimensions.
An Asymmetric Loss with Anomaly Detection LSTM Framework for Power Consumption Prediction
Building an accurate load forecasting model with minimal underpredictions is vital to prevent any undesired power outages due to underproduction of electricity.
Spatio-Temporal Graph Neural Networks: A Survey
These powerful algorithms expanded deep learning models to non-Euclidean space and were able to achieve state of art performance in various applications including recommender systems and social networks.
CEnt: An Entropy-based Model-agnostic Explainability Framework to Contrast Classifiers' Decisions
Our Contrastive Entropy-based explanation method, CEnt, approximates a model locally by a decision tree to compute entropy information of different feature splits.
Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations
Accordingly, we extend the computation of three metrics, proximity, connectedness and stability, to textual data and we benchmark two successful contrastive methods, POLYJUICE and MiCE, on our suggested metrics.
On the Explainability of Natural Language Processing Deep Models
Such challenges can be attributed to the lack of input structure in textual data, the use of word embeddings that add to the opacity of the models and the difficulty of the visualization of the inner workings of deep models when they are trained on textual data.
On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations
In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the explainability of SA models from two angles.
The Power of Transfer Learning in Agricultural Applications: AgriNet
Additionally, all proposed models were found to accurately classify the 423 classes of plant species, diseases, pests, and weeds with a minimum accuracy of 87% for the Inception-v3 model. Finally, experiments to evaluate of superiority of AgriNet models compared to ImageNet models were conducted on two external datasets: pest and plant diseases dataset from Bangladesh and a plant diseases dataset from Kashmir.
Towards Cross-Disaster Building Damage Assessment with Graph Convolutional Networks
In the aftermath of disasters, building damage maps are obtained using change detection to plan rescue operations.
BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledge
While convolutional neural networks are at the core of recent change detection solutions, we present in this work, BLDNet, a novel graph formulation for building damage change detection and enable learning relationships and representations from both local patterns and non-stationary neighborhoods.
Learning to run a Power Network Challenge: a Retrospective Analysis
Motivated to investigate the potential of AI methods in enabling adaptability in power network operation, we have designed a L2RPN challenge to encourage the development of reinforcement learning solutions to key problems present in the next-generation power networks.
Generative Adversarial Stacked Autoencoders for Facial Pose Normalization and Emotion Recognition
In this work, we propose a novel Generative Adversarial Stacked Autoencoder that learns to map facial expressions, with up to plus or minus 60 degrees, to an illumination invariant facial representation of 0 degrees.
An Optimized and Energy-Efficient Parallel Implementation of Non-Iteratively Trained Recurrent Neural Networks
Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions.
Change your singer: a transfer learning generative adversarial framework for song to song conversion
Transfer learning improves the GV by 35% and the MS by 13% on average.
