Donating to SPU |   053 491 0000 |   [email protected] |   Vacancies View current jobs |   Employee Portal

NAS Seminar Series 2023 (Fourth Talk)

The NAS Research Committee invites you to the Fourth Talk in the NAS Seminar Series 2023 that will take place on Thursday, 31 August 2023.

Event Details:

Title: Investigating the Effect of Activation Functions and Sample Sizes on the Performance of Artificial Neural Network Models Through Simulation

Speaker: Dr Alexander Boateng, University of the Free State  

Date: Thursday, 31 August 2023   

Time: 15:30 – 16:30   

Venue: Microsoft Teams, link: Click here to join the meeting

Talk Summary:

Artificial Neural Networks (ANNs) have gained immense recognition as a powerful tool for a wide range of applications, including image recognition, natural language processing, and predictive modelling. Their capacity to decipher intricate patterns and relationships within data makes them highly sought-after. However, the effectiveness of ANNs heavily relies on the choice of activation function and the size of the training dataset. Consequently, this study sought to investigate the impact of activation functions and sample sizes on the performance of artificial neural network models through simulation. The Tanh, Logistic, ReLU, and Identity activation functions were compared in terms of accuracy and training time across diverse sample sizes. Notably, the Tanh activation function consistently showcased superior accuracy levels, ranging from 50% to 97%, surpassing the performance of the other activation functions. However, statistical analysis using ANOVA revealed no significant differences among the mean accuracy values for all activation functions, suggesting that the choice of activation function may not have a substantial impact on overall accuracy. Interestingly, the identity activation function demonstrated significantly shorter training times, averaging 0.27 seconds, in comparison to the Tanh activation function’s 1.66 seconds. Nevertheless, ANOVA analysis indicated no significant disparities among the mean training times for all activation functions, implying that the selection of activation function does not significantly affect training time. These findings provide valuable insights into the influence of activation functions and sample sizes on ANN performance, offering guidance for the selection of appropriate activation functions and sample sizes in different applications. Future research endeavours may explore the impact of other parameters on neural network performance and investigate the optimization of neural network architectures tailored to specific applications. 

More to explore

SPU hosts USSA Football Tournament

We are excited to announce that Sol Plaatje University (SPU) will host the National USSA Football Championships from 2 – 6 December 2024. This prestigious event will bring together 22 universities from the country to compete in one of the

SPU lecturer to advance linguistic diversity on PanSALB language body

Ms Jerida Malatji, a lecturer in Court Interpreting at SPU Faculty of Humanities, has been appointed to serve on the Pan South African Language Board (PanSALB) Sesotho sa Leboa National Language Body for a five-year term. This prestigious appointment underscores

SPU Launches High-Performance Sport Centre

On 22 November 2024, Sol Plaatje University (SPU) proudly launched its High-Performance Sport Centre (HPC) at the South Campus Sport Precinct. This milestone signifies a historic first for the Northern Cape, addressing the need for a world-class sporting facility that

Be the first to write a review

Leave a Reply

Your email address will not be published. Required fields are marked *