Minimizing Parameter Overhead in Self-Supervised Models for Target Task

Kishore, Jaydeep; Mukherjee, Snehasis

doi:10.1109/tai.2023.3322394

Cited by 2 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They tested this approach with SimClr and SWAV on datasets like CIFAR-10, CIFAR-100, and Tiny ImageNet, and the results looked promising in comparison to other methods. Furthermore, this study was expanded by employing Neural Architecture Search (NAS) to optimize the number of parameters [26]. NAS aids in identifying a suitable neural network tailored to specific tasks, thereby reducing the human effort required to discover an optimal architecture for the given task [27].…”

Section: Table 1 Current Advancements In Hyperparameter Optimizationmentioning

confidence: 99%

Optimized Convolutional Neural Network Using Hierarchical Particle Swarm Optimization for Sensor Based Human Activity Recognition

Ankalaki,

Thippeswamy

2024

SN COMPUT. SCI.

View full text Add to dashboard Cite

Hyperparameter optimization poses a significant challenge when developing deep neural networks. Building a convolutional neural network (CNN) for implementation can be an arduous and time-intensive task. This work proposed an approach to optimize the hyperparameters of one dimensional (1D-CNN) to improve the accuracy of human activity recognition (HAR). The framework includes a parametric depiction of 1D-CNNs along with an optimization process for hyperparameters aimed at maximizing the model's performance. This work designed the method called OPTConvNet for hyperparameter optimization of 1D-CNN using Hierarchical Particle Swarm Optimization (H-PSO). The H-PSO algorithm is designed to optimize the architectural, layer and training parameters of 1D-CNN. The H-PSO optimizes the architecture of the 1D-CNN at initial level. Layer and training hyperparameters will be optimized at the next level. The proposed approach employs an exponential-like inertia weight to fine-tune the balance between exploration and exploitation of particles to prevent premature convergence to a local optimum solution in the PSO algorithm. The H-PSO- CNN is evaluated on publicly available sensor- human activity recognition (S-HAR) datasets namely, UCI-HAR, Daphnet Gait, Opportunity and PAMPA2 datasets.

show abstract

Section: Table 1 Current Advancements In Hyperparameter Optimizationmentioning

confidence: 99%