Auto Added by WPeMatico
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.
Winner takes all: A look at activations and cost functions Read More »
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 typical implementation that maximizes the evidence lower bound. Then, we compare it to one of the more recent competitors, MMD-VAE, from the Info-VAE (information maximizing
Representation learning with MMD-VAE Read More »
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 to it in several posts. Here we start with the simpler tasks of naming and locating a single object.
Naming and locating objects in images Read More »
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 test time. In this post, we introduce a refined version of this method (Gal et al. 2017) that has the network itself learn how uncertain
You sure? A Bayesian approach to obtaining uncertainty estimates from neural networks Read More »
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 possible use cases, also drawing attention to what not to expect.
Entity embeddings for fun and profit Read More »
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 same with general object detection, though – naming and locating several objects at once, with no prior information about how many objects are supposed to
Concepts in object detection Read More »
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, we provide a short introduction to the distributions layer and then, use it for sampling and calculating probabilities in a Variational Autoencoder.
Getting started with TensorFlow Probability from R Read More »
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 in van den Oord et al’s “Neural Discrete Representation Learning” features a discrete latent space that allows to learn impressively concise latent representations. In this
Discrete Representation Learning with VQ-VAE and TensorFlow Probability Read More »
As sequence to sequence prediction tasks get more involved, attention mechanisms have proven helpful. A prominent example is neural machine translation. Following a recent Google Colaboratory notebook, we show how to implement attention in R.
Attention-based Neural Machine Translation with Keras Read More »
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 improve prediction, but constitutes a fascinating topic in itself. One such case is audio classification. In this post, we build on a previous post on
Audio classification with Keras: Looking closer at the non-deep learning parts Read More »
