| Virual Oral Presentation Slide by Slide |
IEEE/ICACT20230243 Slide.20
[Big Slide]
[YouTube] |
Oral Presentation |
|
|
The second figure shows the impact of learning rate on algorithm performance, When the learning rate is too high, the neural network cannot converge due to the parameters oscillating out of the valid range. When the learning rate is too low, the algorithm is easy to converge to the local optimum which results suboptimal performance, and the convergence speed is slow. | |
| [Go to Next Slide] |