SPAM detection using fastai ULMFiT – Part 1: Language Model
Tutorial to fastai ULMFiT model for classification texts (and some of the theory behind it) 🤖📚continue reading.
Category: Deep learning
Deep Learning – Überblick und Einstieg
Welche Möglichkeiten und Anwendungen bietet das Thema Deep Learning heutzutage? Wie verschafft man sich einen guten Überblick und wie gelingt der Einstieg? Zum Beispiel mit dem STATWORX Deep Learning Bootcamp!...continue reading.
What’s cooking at STATWORX?
Besides working hard to provide our clients with cutting-edge Machine Learning solutions, we are also big fans of all things culinary here at STATWORX. But can we apply some of...continue reading.
Merge MLP And CNN in Keras
In the post (https://statcompute.wordpress.com/2017/01/08/an-example-of-merge-layer-in-keras), it was shown how to build a merge-layer DNN by using the Keras Sequential model. In the example below, I tried to scratch a merge-layer DNN...continue reading.
Why R? Warsaw 2019 Recap
I’m after an exhausting yet exciting weekend with the WhyR? conference. That was the third edition, this year held in Warsaw, and it is nice to see how it grows...continue reading.
Improve GRNN by Weighting
In the post (https://statcompute.wordpress.com/2019/07/14/yet-another-r-package-for-general-regression-neural-network), several advantages of General Regression Neural Network (GRNN) have been discussed. However, as pointed out by Specht, a major weakness of GRNN is the high computational...continue reading.
Can we get hyper-local infrastructure time series with StreetView and deep learning?
More Google StreetView ideas. Suppose you wanted a measure of infrastructure investment, or of fragility because maintenance has been cut … Morecontinue reading.
Jugando con las dimensiones: desde Clustering, PCA, t-SNE…. ¡hasta Carl Sagan!
Explora la intersección de conceptos como reducción de dimensiones, clustering, preparación de datos, PCA, HDBSCAN, k-NN, SOM, deep learning….y Carl Sagan!continue reading.
Using Reinforcement Learning to play Super Mario Bros on NES using TensorFlow
Could you #BeatTheAI? We let deep learning have a go at Super Mario’s first level and compared it to human players. Here we explain how we did it! Der Beitrag...continue reading.
Bayesian Optimization for Hyper-Parameter
In past several weeks, I spent a tremendous amount of time on reading literature about automatic parameter tuning in the context of Machine Learning (ML), most of which can be...continue reading.
Direct Optimization of Hyper-Parameter
In the previous post (https://statcompute.wordpress.com/2019/02/03/sobol-sequence-vs-uniform-random-in-hyper-parameter-optimization), it is shown how to identify the optimal hyper-parameter in a General Regression Neural Network by using the Sobol sequence and the uniform random generator...continue reading.
Investigating words distribution with R – Zipf’s law
Hello again! Typically I would start by describing a complicated problem that can be solved using machine or deep learning methods, but today I want to do something different, I...continue reading.
Selecting ‘special’ photos on your phone
At the beginning of the new year I always want to clean up my photos on my phone. It just never happens. So now (like so many others I think)...continue reading.
Satellite imagery generation with Generative Adversarial Networks (GANs)
What are GANs? Some time ago, I showed you how to create a simple Convolutional Neural Network (ConvNet) for satellite imagery classification using Keras. ConvNets are not the only cool...continue reading.
Yet Another Tutorial on Variational Auto Encoder – but in Pytorch 1.0
VAE is a generative model that leverages Neural Network as function approximator to model a continuous latent variable with intractable posterior distribution. If you are interested in the theory of...continue reading.
My Selected papers from NIPS 2018 (Neurips’18)
I attended NIPS’18 in Montreal and here is the list of papers that I found interesting from the talks and poster sessions:Generatives And Adverserial:GILBO: One Metric to Measure Them AllOn...continue reading.
Dataviz and methodviz of the year, 2018
Dataviz of the year goes to Nadieh Bremer, Shirley Wu and journalist collaborators for “Bussed Out“, a Guardian US article … Morecontinue reading.
Deep learning in Satellite imagery
In this article, I hope to inspire you to start exploring satellite imagery datasets. Recently, this technology has gained huge momentum, and we are finding that new possibilities arise when...continue reading.
Using Recurrent Neural Nets to Generate Band Names
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.
Building a scaleable Deep Learning Serving Environment for Keras models using NVIDIA TensorRT Server and Google Cloud
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.
