Sometimes, deep learning is seen – and welcomed – as a way to avoid laborious preprocessing of data. However, there are cases where preprocessing of sorts does not only help...continue reading.
Mostly when thinking of Variational Autoencoders (VAEs), we picture the prior as an isotropic Gaussian. But this is by no means a necessity. The Vector Quantised Variational Autoencoder (VQ-VAE) described...continue reading.
TensorFlow Probability offers a vast range of functionality ranging from distributions over probabilistic network layers to probabilistic inference. It works seamlessly with core TensorFlow and (TensorFlow) Keras. In this post,...continue reading.
As shown in a previous post, naming and locating a single object in an image is a task that may be approached in a straightforward way. This is not the...continue reading.
In this post we will return to the Pitchfork music data and use recurrent neural networks (a “deep learning” technique) to automatically generate band names.The DataFor this analysis, we will...continue reading.
Embedding layers are not just useful when working with language data. As “entity embeddings”, they’ve recently become famous for applications on tabular, small-scale data. In this post, we exemplify two...continue reading.
In a recent project at STATWORX, my team and I developed a large scale deep learning application for image classification using Keras and Tensorflow. After developing the model, we needed...continue reading.
In deep learning, there is no obvious way of obtaining uncertainty estimates. In 2016, Gal and Ghahramani proposed a method that is both theoretically grounded and practical: use dropout at...continue reading.
Object detection (the act of classifying and localizing multiple objects in a scene) is one of the more difficult, but very relevant in practice deep learning tasks. We’ll build up...continue reading.
Like GANs, variational autoencoders (VAEs) are often used to generate images. However, VAEs add an additional promise: namely, to model an underlying latent space. Here, we first look at a...continue reading.
STATWORX welcomes you to our open workshop “Deep Learning in R and Keras” ! The workshop is designed for advanced R-users who are fluent in importing, processing and manipulating data....continue reading.
Last Christmas is one of the most popular Christmas tunes that were, are and will be out there. The song is written by the brilliant musician George Michael and was...continue reading.
Why do we use the activations we use, and how do they relate to the cost functions they tend to co-appear with? In this post we provide a conceptual introduction.continue reading.
Advanced applications like generative adversarial networks, neural style transfer, and the attention mechanism ubiquitous in natural language processing used to be not-so-simple to implement with the Keras declarative coding paradigm....continue reading.
Embeddings are not just for use in natural language processing. Here we apply embeddings to a common task in collaborative filtering – predicting user ratings – and on our way,...continue reading.
Conditional GANs (cGANs) may be used to generate one type of object based on another – e.g., a map based on a photo, or a color video based on black-and-white....continue reading.
Image captioning is a challenging task at intersection of vision and language. Here, we demonstrate using Keras and eager execution to incorporate an attention mechanism that allows the network to...continue reading.
Image captioning is a challenging task at intersection of vision and language. Here, we demonstrate using Keras and eager execution to incorporate an attention mechanism that allows the network to...continue reading.
This tutorial will introduce the Deep Learning classification task with Keras. With focus on one-hot encoding, layer shapes, train & model evaluation.continue reading.
Continuing our series on combining Keras with TensorFlow eager execution, we show how to implement neural style transfer in a straightforward way. Based on this easy-to-adapt example, you can easily...continue reading.
