Debugging image classification algorithms using human assisted feedback

Download

Kadircan_Becek_Thesis.pdf

Date

2022-12-15

Author

Becek, Kadircan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

192
views

139
downloads

Neural Network debugging is a relatively newly emerged field of deep learning which tries to improve upon learned parameters with external assistance. Two academic fields are particularly active in addressing this issue: the field of feature visualiza- tions and explainable artificial intelligence. While these methods can improve how to interpret a neural network, they can not provide the expert opinion of a human to improve the accuracy of a neural network. Therefore, while being interpreted cor- rectly, these networks can have undesired outputs. For instance, they may have biases against some classes or may not work effectively in the wild due to overfitting. In this thesis, we propose a method with two steps to tackle this problem: (1) present- ing feature contribution using visualization, (2) taking feedback from humans, and retraining the network by disabling irrelevant or adversarial features.

Subject Keywords

Explainable AI, Feature visualization, Debugging

URI

https://hdl.handle.net/11511/101260

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Competing labels: a heuristic approach to pseudo-labeling in deep semi-supervised learning Bayrak, Hamdi Burak; Ertekin Bolelli, Şeyda; Yücel, Hamdullah; Department of Scientific Computing (2022-2-10) Semi-supervised learning is one of the dominantly utilized approaches to reduce the reliance of deep learning models on large-scale labeled data. One mostly used method of this approach is pseudo-labeling. However, pseudo-labeling, especially its originally proposed form tends to remarkably suffer from noisy training when the assigned labels are false. In order to mitigate this problem, in our work, we investigate the gradient sent to the neural network and propose a heuristic method, called competing label...
Deep Learning-Based Hybrid Approach for Phase Retrieval IŞIL, ÇAĞATAY; Öktem, Sevinç Figen; KOÇ, AYKUT (2019-06-24) We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.
MetaLabelNet: Learning to Generate Soft-Labels From Noisy-Labels Algan, Gorkem; Ulusoy, İlkay (2022-01-01) Real-world datasets commonly have noisy labels, which negatively affects the performance of deep neural networks (DNNs). In order to address this problem, we propose a label noise robust learning algorithm, in which the base classifier is trained on soft-labels that are produced according to a meta-objective. In each iteration, before conventional training, the meta-training loop updates soft-labels so that resulting gradients updates on the base classifier would yield minimum loss on meta-data. Soft-labels...
A temporal neural network model for constructing connectionist expert system knowledge bases Alpaslan, Ferda Nur (Elsevier BV, 1996-04-01) This paper introduces a temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications.
Automated learning rate search using batch-level cross-validation KABAKÇI, Duygu; Akbaş, Emre (2021-04-01) Deep learning researchers and practitioners have accumulated a significant amount of experience on training a wide variety of architectures on various datasets. However, given anetwork architecture and a dataset, obtaining the best model (i.e. the model giving the smallest test set error) while keeping the training time complexity low is still a challenging task. Hyper-parameters of deep neural networks, especially the learning rate and its (decay) schedule, highly affect the network's final performance. Th...

Citation Formats

K. Becek, “Debugging image classification algorithms using human assisted feedback,” M.S. - Master of Science, Middle East Technical University, 2022.