no code implementations • 4 Jan 2024 • Peng-Hung Tsai, Daniel Berleant, Richard S. Segall, Hyacinthe Aboudja, Venkata Jaipal R. Batthula, Sheela Duggirala, Michael Howell
A widely used approach in this field is trend extrapolation.
no code implementations • 26 Nov 2023 • Wei Dai, Daniel Berleant
In the context of deep learning research, where model introductions continually occur, the need for effective and efficient evaluation remains paramount.
no code implementations • 13 Jun 2023 • Venkat Kodali, Daniel Berleant
Superimposed text annotations have been under-investigated, yet are ubiquitous, useful and important, especially in medical images.
no code implementations • 20 Nov 2022 • Girish Sundaram, Daniel Berleant
Results: This review identifies the objectives of the automation studies, steps within the study selection, study quality assessment, data extraction and data synthesis portions that were automated, the various ML techniques used, challenges, limitations and scope of further research.
no code implementations • 19 Oct 2022 • Wei Dai, Daniel Berleant
After quantitatively analyzing experimental results, we report the limitations of the two IQAs with these noised CIFAR-10 and MNIST image sets.
no code implementations • 2 Mar 2022 • Wei Dai, Daniel Berleant
We created comprehensive 69 benchmarking image sets, including a clean set, sets with single factor perturbations, and sets with two-factor perturbation conditions.
no code implementations • 2 Mar 2022 • Venkat Kodali, Daniel Berleant
Understanding visual question answering is going to be crucial for numerous human activities.
no code implementations • 8 Jul 2021 • Daniel Berleant, Venkat Kodali, Richard Segall, Hyacinthe Aboudja, Michael Howell
A frequently noted competitor to Moore's law is known as Wright's law, which has aeronautical roots.
2 code implementations • 2 Mar 2021 • Wei Dai, Daniel Berleant
Also, we introduce a new four-quadrant statistical visualization tool, including minimum accuracy, maximum accuracy, mean accuracy, and coefficient of variation, for benchmarking robustness of DL classifiers.
1 code implementation • 5 Jul 2019 • Wei Dai, Daniel Berleant
This paper surveys benchmarking principles, machine learning devices including GPUs, FPGAs, and ASICs, and deep learning software frameworks.