Training deep neural networks with tens of layers is challenging as they can be sensitive to the initial random weights and configuration of the learning algorithm. One possible reason for this difficulty is the distribution of the inputs to layers deep in the network may change after each mini-batch when the weights are updated. This […]

# Archive | Better Deep Learning

## 3 Must-Own Books for Deep Learning Practitioners

Developing neural networks is often referred to as a dark art. The reason for this is that being skilled at developing neural network models comes from experience. There are no reliable methods to analytically calculate how to design a “good” or “best” model for your specific dataset. You must draw on experience and experiment in […]

## How to Fix the Vanishing Gradients Problem Using the Rectified Linear Unit (ReLU)

The vanishing gradients problem is one example of unstable behavior that you may encounter when training a deep neural network. It describes the situation where a deep multilayer feed-forward network or a recurrent neural network is unable to propagate useful gradient information from the output end of the model back to the layers near the […]

## A Gentle Introduction to the Rectified Linear Unit (ReLU) for Deep Learning Neural Networks

In a neural network, the activation function is responsible for transforming the summed weighted input from the node into the activation of the node or output for that input. The rectified linear activation function is a piecewise linear function that will output the input directly if is positive, otherwise, it will output zero. It has […]

## How to Create an Equally, Linearly, and Exponentially Weighted Average of Neural Network Model Weights in Keras

The training process of neural networks is a challenging optimization process that can often fail to converge. This can mean that the model at the end of training may not be a stable or best-performing set of weights to use as a final model. One approach to address this problem is to use an average […]

## How to Develop a Snapshot Ensemble Deep Learning Neural Network in Python With Keras

Model ensembles can achieve lower generalization error than single models but are challenging to develop with deep learning neural networks given the computational cost of training each single model. An alternative is to train multiple model snapshots during a single training run and combine their predictions to make an ensemble prediction. A limitation of this […]

## Impact of Dataset Size on Deep Learning Model Skill And Performance Estimates

Supervised learning is challenging, although the depths of this challenge are often learned then forgotten or willfully ignored. This must be the case, because dwelling too long on this challenge may result in a pessimistic outlook. In spite of the challenge, we continue to wield supervised learning algorithms and they perform well in practice. Fundamental […]

## How to Develop a Stacking Ensemble for Deep Learning Neural Networks in Python With Keras

Model averaging is an ensemble technique where multiple sub-models contribute equally to a combined prediction. Model averaging can be improved by weighting the contributions of each sub-model to the combined prediction by the expected performance of the submodel. This can be extended further by training an entirely new model to learn how to best combine […]

## How to Develop a Weighted Average Ensemble for Deep Learning Neural Networks

A modeling averaging ensemble combines the prediction from each model equally and often results in better performance on average than a given single model. Sometimes there are very good models that we wish to contribute more to an ensemble prediction, and perhaps less skillful models that may be useful but should contribute less to an […]

## How to Develop a Horizontal Voting Deep Learning Ensemble to Reduce Variance

Predictive modeling problems where the training dataset is small relative to the number of unlabeled examples are challenging. Neural networks can perform well on these types of problems, although they can suffer from high variance in model performance as measured on a training or hold-out validation datasets. This makes choosing which model to use as […]