Search Results for author:
Found 9 papers, 3 papers with code
Counterfactual Image Generation for adversarially robust and interpretable Classifiers
Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks.
MAEDAY: MAE for few and zero shot AnomalY-Detection
We propose using Masked Auto-Encoder (MAE), a transformer model self-supervisedly trained on image inpainting, for anomaly detection (AD).
Generating Efficient DNN-Ensembles with Evolutionary Computation
In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models.
Constrained deep neural network architecture search for IoT devices accounting for hardware calibration
The narrow-space search of floating-point models improves the accuracy on CIFAR10 of an established IoT model from 70. 64% to 74. 87% within the same memory constraints.
Constrained deep neural network architecture search for IoT devices accounting hardware calibration
We further improve the accuracy to 82. 07% by including 16-bit half types and we obtain the best accuracy of 83. 45% by extending the search with model optimized IEEE 754 reduced types.
PAGAN: Portfolio Analysis with Generative Adversarial Networks
Sound financial theories demonstrate that in an efficient marketplace all information available today, including expectations on future events, are represented in today prices whereas future price trend is driven by the uncertainty.
Computational Finance Statistical Finance
NeuNetS: An Automated Synthesis Engine for Neural Network Design
Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice.
Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracy
In the deep-learning community new algorithms are published at an incredible pace.
BAGAN: Data Augmentation with Balancing GAN
The generator in the GAN is initialized with the encoder module of an autoencoder that enables us to learn an accurate class-conditioning in the latent space.
