# Paper
###### tags: `賴` `CNN` `hyper-parameter`

[Google Drive](https://drive.google.com/drive/u/1/folders/1CRvI2h55_kd-Vo_HSg0mdLZQWVgnZJhB)

1. [Optimization of hyper-parameter for CNN model using genetic algorithm](https://ieeexplore.ieee.org/document/8974762)
~~[Hyper-parameter Determination of CNN Classifier for Head Pose Estimation of Three Dimensional Degraded Face Images](https://ieeexplore.ieee.org/document/8982142)~~
3. [Hyper-Parameter Selection in Convolutional Neural Networks Using Microcanonical Optimization Algorithm](https://ieeexplore.ieee.org/document/9037322)
4. [Speeding up the Hyperparameter Optimization of DeepConvolutional Neural Networks](https://www.worldscientific.com/doi/epdf/10.1142/S1469026818500086)
5. [Weighted Random Search for CNN Hyperparameter Optimization](https://arxiv.org/ftp/arxiv/papers/2003/2003.13300.pdf)
6. [Hyperparameter Optimization in Convolutional Neural Network using Genetic Algorithms
](https://pdfs.semanticscholar.org/c02f/877d81f487106cbd437f3f8d46b1496a897f.pdf)
7. [HYPER-PARAMETER OPTIMIZATION FOR CONVOLUTIONAL NEURAL NETWORK COMMITTEES BASED ON EVOLUTIONARY ALGORITHMS](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8297018)
8. [Hybrid MPSO-CNN: Multi-level Particle Swarm optimized hyperparameters of Convolutional Neural Network](https://www.sciencedirect.com/science/article/pii/S2210650221000249)
9. [Convolutional Neural Network Hyperparameter Tuning with Adam Optimizer for ECG Classification](https://ieeexplore.ieee.org/document/9259896)
10. [Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm](https://www.sciencedirect.com/science/article/pii/S0030402618310167)
11. [CNN Optimization with a Genetic Algorithm](https://ieeexplore.ieee.org/document/9058307)
12. [Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification](https://ieeexplore.ieee.org/document/9075201)
13. [Hybrid models based on genetic algorithm and deep learning algorithms for nutritional Anemia disease classification](https://www.sciencedirect.com/science/article/pii/S174680942030361X)
14. [ExperienceThinking: Constrained hyperparameter optimization based on knowledge and pruning](https://www.sciencedirect.com/science/article/pii/S0950705120307310)

## Parameter

### Conv2D
**filters** *5
**kernel_size** *6
**strides=(1, 1)** *5
**padding='valid'** *3
data_format=None
dilation_rate=(1, 1)
groups=1
**activation=None** ~~*3~~ 4
use_bias=True
kernel_initializer='glorot_uniform'
bias_initializer='zeros'
kernel_regularizer=None
bias_regularizer=None
activity_regularizer=None
kernel_constraint=None
bias_constraint=None

### MaxPooling2D
**pool_size=(2, 2)** *4
**strides=None** *4
padding='valid'
data_format=None

### Flatten
data_format=None

### number of each layer
**conv** *6
**pooling** *2

### dropout
**rate** *2
noise_shape=None
seed=None

### dense
**units** *3
**activation=None** ~~*4~~ 2
use_bias=True
kernel_initializer='glorot_uniform'
bias_initializer='zeros'
kernel_regularizer=None
bias_regularizer=None
activity_regularizer=None
kernel_constraint=None
bias_constraint=None

**batch_size** *3
steps_per_epochs
**learning_rate** *5

epochs