I obtained the image data from Unsplash. I downloaded 42 cat images, 46 dog images, and 35 horse images for the input into the pre-trained Alexnet model in MATLAB. For details about the Alexnet network in MATLAB, see its documentation.

Transfer learning using the pre-trained deep learning networks from MATLAB can be easily implemented to achieve fast and impressive results


Alexnet

AlexNet is a convolutional neural network that is 8 layers deep. The MATLAB has a pre-trained version of the network trained on more than a million images from the ImageNet database. The pre-trained network can classify images into 1000 predefined object categories.

The training for the 1000 object categories on a million images has made the network learn rich feature representations for a wide range of images.

For codes and details, visit my blog post:

https://www.earthinversion.com/machinelearning/transfer-learning-applied-on-unsplash-data-using-alexnet/