no code implementations • 3 May 2024 • Sander Dalm, Joshua Offergeld, Nasir Ahmad, Marcel van Gerven
This demonstrates that decorrelation provides exciting prospects for efficient deep learning at scale.
no code implementations • 1 May 2024 • Ayaz Mehmood, Muhammad Tayyab Zamir, Muhammad Asif Ayub, Nasir Ahmad, Kashif Ahmad
To fully explore the potential of social media content in disaster informatics, access to relevant content and the correct geo-location information is very critical.
no code implementations • 23 Apr 2024 • Muhammad Asif Auyb, Muhammad Tayyab Zamir, Imran Khan, Hannia Naseem, Nasir Ahmad, Kashif Ahmad
To ensure the quality of water, different methods for monitoring and assessing the water networks, such as offline and online surveys, are used.
no code implementations • 12 Jan 2024 • Muhammad Tayyab Zamir, Muhammad Asif Ayub, Asma Gul, Nasir Ahmad, Kashif Ahmad
This paper investigates three key tasks of style analysis: (i) classification of single and multi-authored documents, (ii) single change detection, which involves identifying the point where the author switches, and (iii) multiple author-switching detection in multi-authored documents.
no code implementations • 2 Oct 2023 • Sander Dalm, Marcel van Gerven, Nasir Ahmad
Backpropagation (BP) is the dominant and most successful method for training parameters of deep neural network models.
no code implementations • 2 Mar 2023 • Muhammad Tayyab Zamir, Muhammad Asif Ayub, Jebran Khan, Muhammad Jawad Ikram, Nasir Ahmad, Kashif Ahmad
In this paper, we propose an ensemble-based text-processing framework for the classification of single and multi-authored documents, which is one of the key tasks in style analysis.
no code implementations • 1 Jan 2023 • Muhammad Suleman, Muhammad Asif, Tayyab Zamir, Ayaz Mehmood, Jebran Khan, Nasir Ahmad, Kashif Ahmad
This paper presents our solutions for the MediaEval 2022 task on DisasterMM.
1 code implementation • 11 Nov 2022 • Burcu Küçükoğlu, Walraaf Borkent, Bodo Rueckauer, Nasir Ahmad, Umut Güçlü, Marcel van Gerven
Predictive processing is a popular theoretical framework which maintains that the human brain is actively seeking to minimize surprise.
no code implementations • 11 Jul 2022 • Maria Shoukat, Khubaib Ahmad, Naina Said, Nasir Ahmad, Mohammed Hassanuzaman, Kashif Ahmad
The extraction of such meaningful information is a complex task and generally, the performance of individual algorithms is very low.
no code implementations • 28 Apr 2022 • Talhat Khan, Kashif Ahmad, Jebran Khan, Imran Khan, Nasir Ahmad
The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components.
1 code implementation • 22 Mar 2022 • Nasir Ahmad, Ellen Schrader, Marcel van Gerven
Backpropagation of error (BP) is an example of such an approach and has proven to be a highly successful application of stochastic gradient descent to deep neural networks.
no code implementations • 9 Feb 2022 • Khubaib Ahmad, Muhammad Asif Ayub, Kashif Ahmad, Jebran Khan, Nasir Ahmad, Ala Al-Fuqaha
We also provide an evaluation of the individual models where the highest F1-score of 0. 81 is obtained with the BERT model.
no code implementations • 30 Nov 2021 • Muhammad Asif Ayub, Khubaib Ahmad, Kashif Ahmad, Nasir Ahmad, Ala Al-Fuqaha
This paper presents our contributions to the MediaEval 2021 task namely "WaterMM: Water Quality in Social Multimedia".
no code implementations • 2 Oct 2021 • Imran Khan, Kashif Ahmad, Namra Gul, Talhat Khan, Nasir Ahmad, Ala Al-Fuqaha
The results of the study indicate that 78%, 84%, and 78% of the model decisions on natural disasters, sports, and social events datasets, respectively, are based onevent-related objects or regions.
no code implementations • 29 Sep 2021 • Burcu Küçükoğlu, Walraaf Borkent, Bodo Rueckauer, Nasir Ahmad, Umut Güçlü, Marcel van Gerven
Predictive processing is a popular theoretical framework which maintains that the human brain is actively seeking to minimize surprise.
no code implementations • 23 Feb 2021 • Sander Dalm, Nasir Ahmad, Luca Ambrogioni, Marcel van Gerven
Many of the recent advances in the field of artificial intelligence have been fueled by the highly successful backpropagation of error (BP) algorithm, which efficiently solves the credit assignment problem in artificial neural networks.
no code implementations • 30 Nov 2020 • Naina Said, Kashif Ahmad, Asma Gul, Nasir Ahmad, Ala Al-Fuqaha
The extracted features are then used to train multiple individual classifiers whose scores are then combined in a late fusion manner achieving an F1-score of 0. 75%.
1 code implementation • NeurIPS 2020 • Nasir Ahmad, Marcel A. J. van Gerven, Luca Ambrogioni
An alternative called target propagation proposes to solve this implausibility by using a top-down model of neural activity to convert an error at the output of a neural network into layer-wise and plausible 'targets' for every unit.
1 code implementation • 9 Mar 2020 • Nasir Ahmad, Luca Ambrogioni, Marcel A. J. van Gerven
We propose a solution to the weight transport problem, which questions the biological plausibility of the backpropagation algorithm.