Python 2: Use Convolutional Neural Network (CNN) to Recognize My Handwriting

This video is going to show how to construct Convolutional Neural Network (CNN) using Keras for image recognition. Parameters to adjust are (1) filter size, (2) number of filters, (3) stride, (4) activation function, (5) padding, (6) loss function, (7) optimizer, (8) metrics for model performance, (9) pooling method, (10) drop out rate, (11) validation size, and some other adjustment for model. Methods used in this example are (1) Rectified Linear Unit (ReLU), (2) Stochastic Gradient Descent, (3) Binary Cross Entropy, (4) Max Pooling, (5) Fully Connected Neural Network. Please refer to Keras and research papers for more information and adjustment for Convolutional Neural Network.

Thanks for watching. My website: http://allenkei.weebly.com

If you like this video please "Like", "Subscribe", and "Share" it with your friends to show your support! If there is something you'd like to see or you have question about it, feel free to let me know in the comment section. I will respond and make a new video shortly for you. Your comments are greatly appreciated.

• #science_technology
• #convolutional_neural_network
• #cnn
• #keras
• #image_recognition