Last Updated on August 25, 2020 An interesting benefit of deep learning neural networks is that they can be reused on related problems. Transfer learning refers to a technique for predictive modeling on a different but somehow similar problem that can then be reused partly or wholly to accelerate the training and improve the performance of a model on the problem of interest. In deep learning, this means reusing the weights in one or more layers from a pre-trained network […]

Last Updated on August 6, 2019 Modern deep learning libraries such as Keras allow you to define and start fitting a wide range of neural network models in minutes with just a few lines of code. Nevertheless, it is still challenging to configure a neural network to get good performance on a new predictive modeling problem. The challenge of getting good performance can be broken down into three main areas: problems with learning, problems with generalization, and problems with predictions. […]

Last Updated on August 25, 2020 The capacity of a deep learning neural network model controls the scope of the types of mapping functions that it is able to learn. A model with too little capacity cannot learn the training dataset meaning it will underfit, whereas a model with too much capacity may memorize the training dataset, meaning it will overfit or may get stuck or lost during the optimization process. The capacity of a neural network model is defined […]

Last Updated on August 6, 2019 Deep learning neural networks learn a mapping function from inputs to outputs. This is achieved by updating the weights of the network in response to the errors the model makes on the training dataset. Updates are made to continually reduce this error until either a good enough model is found or the learning process gets stuck and stops. The process of training neural networks is the most challenging part of using the technique in […]

Last Updated on January 8, 2020 Better Deep Learning Neural Networks Crash Course. Get Better Performance From Your Deep Learning Models in 7 Days. Configuring neural network models is often referred to as a “dark art.” This is because there are no hard and fast rules for configuring a network for a given problem. We cannot analytically calculate the optimal model type or model configuration for a given dataset. Fortunately, there are techniques that are known to address specific issues […]

Last Updated on August 6, 2019 Deep learning neural networks are challenging to configure and train. There are decades of tips and tricks spread across hundreds of research papers, source code, and in the heads of academics and practitioners. The book “Neural Networks: Tricks of the Trade” originally published in 1998 and updated in 2012 at the cusp of the deep learning renaissance ties together the disparate tips and tricks into a single volume. It includes advice that is required […]

Last Updated on August 6, 2019 Neural network models are trained using stochastic gradient descent and model weights are updated using the backpropagation algorithm. The optimization solved by training a neural network model is very challenging and although these algorithms are widely used because they perform so well in practice, there are no guarantees that they will converge to a good model in a timely manner. The challenge of training neural networks really comes down to the challenge of configuring […]

Last Updated on August 6, 2019 Deep learning neural networks are relatively straightforward to define and train given the wide adoption of open source libraries. Nevertheless, neural networks remain challenging to configure and train. In his 2012 paper titled “Practical Recommendations for Gradient-Based Training of Deep Architectures” published as a preprint and a chapter of the popular 2012 book “Neural Networks: Tricks of the Trade,” Yoshua Bengio, one of the fathers of the field of deep learning, provides practical recommendations […]

Last Updated on August 6, 2019 A learning curve is a plot of model learning performance over experience or time. Learning curves are a widely used diagnostic tool in machine learning for algorithms that learn from a training dataset incrementally. The model can be evaluated on the training dataset and on a hold out validation dataset after each update during training and plots of the measured performance can created to show learning curves. Reviewing learning curves of models during training […]

Last Updated on August 6, 2019 Or, Why Stochastic Gradient Descent Is Used to Train Neural Networks. Fitting a neural network involves using a training dataset to update the model weights to create a good mapping of inputs to outputs. This training process is solved using an optimization algorithm that searches through a space of possible values for the neural network model weights for a set of weights that results in good performance on the training dataset. In this post, […]