Archive | Deep Learning

Example MNIST images

Image Augmentation for Deep Learning with Keras

Data preparation is required when working with neural networks and deep learning models. Increasingly, data augmentation is also required on more complex object recognition tasks. In this post, you will discover how to use data preparation and data augmentation with your image datasets when developing and evaluating deep learning models in Python with Keras. After […]

Continue Reading 188
Loss function

Loss Functions in TensorFlow

The loss metric is very important for neural networks. As all machine learning models are one optimization problem or another, the loss is the objective function to minimize. In neural networks, the optimization is done with gradient descent and backpropagation. But what are loss functions, and how are they affecting your neural networks? In this […]

Continue Reading 2

Understanding the Design of a Convolutional Neural Network

Convolutional neural networks have been found successful in computer vision applications. Various network architectures are proposed, and they are neither magical nor hard to understand. In this tutorial, you will make sense of the operation of convolutional layers and their role in a larger convolutional neural network. After finishing this tutorial, you will learn: How […]

Continue Reading 0
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