ﻻ يوجد ملخص باللغة العربية
We introduce feature alignment, a technique for obtaining approximate reversibility in artificial neural networks. By means of feature extraction, we can train a neural network to learn an estimated map for its reverse process from outputs to inputs. Combined with variational autoencoders, we can generate new samples from the same statistics as the training data. Improvements of the results are obtained by using concepts from generative adversarial networks. Finally, we show that the technique can be modified for training neural networks locally, saving computational memory resources. Applying these techniques, we report results for three vision generative tasks: MNIST, CIFAR-10, and celebA.
Generalisation of a deep neural network (DNN) is one major concern when employing the deep learning approach for solving practical problems. In this paper we propose a new technique, named approximated orthonormal normalisation (AON), to improve the
Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such networks follows mostly the supervised learning paradigm, whe
Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. On one hand, massive trainable parameters significantly enhance the performance of these deep networks. On the other ha
Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a certain pattern
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution di