Evaluating Model Performance with Hard-Swish Activation Function Adjustments
Nguyen, H. P.
Show abstract
In the field of pattern recognition, achieving high accuracy is essential. While training a model to recognize different complex images, it is vital to fine-tune the model to achieve the highest accuracy possible. One strategy for fine-tuning a model involves changing its activation function. Most pre-trained models use ReLU as their default activation function, but switching to a different activation function like Hard-Swish could be beneficial. This study evaluates the performance of models using ReLU, Swish and Hard-Swish activation functions across diverse image datasets. Our results show a 2.06% increase in accuracy for models on the CIFAR-10 dataset and a 0.30% increase in accuracy for models on the ATLAS dataset. Modifying the activation functions in architecture of pre-trained models lead to improved overall accuracy.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- A novel interpretable deep transfer learning combining diverse learnable parameters for improved T2D prediction based on single-cell gene regulatory networks 96%
- WormSwin: Instance segmentation of C. elegans using vision transformer 94%
- An Assistive Computer Vision Tool to Automatically Detect Changes in Fish Behavior In Response to Ambient Odor 94%
Similar papers in this journal
- 3D-MASNet: 3D Mixed-scale Asymmetric Convolutional Segmentation Network for 6-month-old Infant Brain MR Images 95%
- Automatic Landmark-guided Bijective Brain Image Registration by Composing Region-based Locally Diffeomorphic Warpings 92%
- DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.