A simple Conv3D example with Keras
These past few years, convolutional neural networks have become known for the boost they gave to machine learning, or artificial...
Tag: deep learning
How to use categorical / multiclass hinge with Keras?
Recently, I’ve been looking into loss functions – and specifically these questions: What is their purpose? How does the concept...
How to use hinge & squared hinge loss with Keras?
In order to discover the ins and outs of the Keras deep learning framework, I’m writing blog posts about commonly...
Leaky ReLU: improving traditional ReLU
The Leaky ReLU is a type of activation function which comes across many machine learning blogs every now and then....
Using Huber loss in Keras
The Huber loss function can be used to balance between the Mean Absolute Error, or MAE, and the Mean Squared...
How to visualize the training process in Keras?
Sometimes, you don’t want to visualize the architecture of your Keras model, but rather you wish to show the training...
How to visualize a model with Keras?
Every now and then, you might need to demonstrate your Keras model structure. There’s one or two things that you...
About loss and loss functions
When you’re training supervised machine learning models, you often hear about a loss function that is minimized; that must be...
Understanding transposed convolutions
Recently, we’ve looked at convolutional layers and certain variations to see how they can be used in machine learning problems....
Creating depthwise separable convolutions in Keras
In a recent blog post, we took a look at separable convolutions. When you separate your convolutional kernels in a...
