Using Learning Rate Schedules for Deep Learning Models in Python with Keras

Using Learning Rate Schedules for Deep Learning Models in Python with Keras

Training a neural network or large deep learning model is a difficult optimization task. The classical algorithm to train neural networks is called stochastic gradient descent. It has been well established that you can achieve increased performance and faster training on some problems by using a learning rate that changes during training. In this post, […]

Continue Reading 55
Using Activation Functions in TensorFlow<br/>Photo by <a href="">Victor Freitas</a>. Some rights reserved.

Using Activation Functions in Neural Networks

Activation functions play an integral role in neural networks by introducing nonlinearity. This nonlinearity allows neural networks to develop complex representations and functions based on the inputs that would not be possible with a simple linear regression model. Many different nonlinear activation functions have been proposed throughout the history of neural networks. In this post, […]

Continue Reading 4

Using Autograd in TensorFlow to Solve a Regression Problem

We usually use TensorFlow to build a neural network. However, TensorFlow is not limited to this. Behind the scenes, TensorFlow is a tensor library with automatic differentiation capability. Hence you can easily use it to solve a numerical optimization problem with gradient descent. In this post, you will learn how TensorFlow’s automatic differentiation engine, autograd, […]

Continue Reading 0
Photo by <a href="">Francesco Ungaro</a>

Overview of Some Deep Learning Libraries

Machine learning is a broad topic. Deep learning, in particular, is a way of using neural networks for machine learning. A neural network is probably a concept older than machine learning, dating back to the 1950s. Unsurprisingly, there were many libraries created for it. The following aims to give an overview of some of the […]

Continue Reading 3