Keras

Twitter Sentiment Analysis with Gensim Word2Vec and Keras Convolutional Networks

/ Leave a Comment

Fork Word2Vec (https://code.google.com/archive/p/word2vec/) offers a very interesting alternative to classical NLP based on term-frequency matrices. In particular, as each word is embedded into a high-dimensional vector, it’s possible to consider a sentence like a sequence of points that determine an implicit geometry. For this reason, the idea of considering 1D convolutional classifiers (usually very efficient … [Read more…]

Machine Learning Algorithms

/ Leave a Comment

My latest machine learning book has been published and will be available during the last week of July. From the back cover: In this book you will learn all the important Machine Learning algorithms that are commonly used in the field of data science. These algorithms can be used for supervised as well as unsupervised … [Read more…]

Keras-based Deepdream experiment based on VGG19

/ Leave a Comment

Fork I’ve just published a repository (https://github.com/giuseppebonaccorso/keras_deepdream) with a Jupyter notebook containing a Deepdream (https://github.com/google/deepdream) experiment created with Keras and a pre-trained VGG19 convolutional network. The experiment (which is a work in progress) is based on some suggestions provided by the Deepdream team in this blog post but works in a slightly different way. I use a Gaussian … [Read more…]

Seq2Seq experiment with mathematical expressions

/ Leave a Comment

After reading the article “How to Learn to Add Numbers with seq2seq Recurrent Neural Networks” by Jason Brownlee (that I suggest reading before going on), I’ve decided to try an experiment with more complex expressions like: -(10+5) or 4+ -2, etc. The code (with some extra information) is published on the GIST: https://goo.gl/ZmH6Tf, where there are … [Read more…]

Keras-based Neural Artistic Style Transfer

/ Leave a Comment

Fork I’ve just moved my Keras-based Neural Artistic Style Transfer GIST to a dedicated repository: https://github.com/giuseppebonaccorso/Neural_Artistic_Style_Transfer. Please refer always to it because the GIST is not more maintained. The original post is: https://www.bonaccorso.eu/2016/11/13/neural-artistic-style-transfer-experiments-with-keras/  

BBC News classification algorithm comparison

/ Leave a Comment

Fork BBC News dataset (available for download in Insight Project Resources website) is made up of 2225 newslines classified into 5 categories (Politics, Sport, Entertainment, Tech, Business) and, similarly to Reuters-21578, it can be adopted in order to test both the efficacy and the efficiency of different classification strategies. In the repository: https://github.com/giuseppebonaccorso/bbc_news_classification_comparison, I’ve committed a Jupyter (IPython) … [Read more…]

Neural artistic style transfer experiments with Keras

/ Leave a Comment

Fork Artistic style transfer using neural networks is a technique proposed by Gatys, Ecker and Bethge in the paper: arXiv:1508.06576 [cs.CV] which exploits a trained convolutional network in order to reconstruct the elements of a picture adopting the artistic style of a particular painting. I’ve written a Python program (available in the Github repository: https://github.com/giuseppebonaccorso/Neural_Artistic_Style_Transfer) … [Read more…]

OpenAI-Gym Cartpole-v0 LSTM experiment with Keras (Theano)

/ 5 Comments

OpenAI-Gym evaluation page: https://gym.openai.com/evaluations/eval_JxPKNwd1QjaofWkaE4aLfQ. Below there’s the whole Gist page containing the full Python code. It has been developed and tested with Theano/GPU support, but it can easily work with CPU-only support. Any comment or suggestion is welcome! View the code on Gist.

CIFAR-10 image classification with Keras ConvNet

/ 5 Comments

(Updated on July, 24th, 2017 with some improvements and Keras 2 style, but still a work in progress) CIFAR-10 is a small image (32 x 32) dataset made up of 60000 images subdivided into 10 main categories. Check the web page in the reference list in order to have further information about it and download … [Read more…]

Reuters-21578 text classification with Gensim and Keras

/ Leave a Comment

Fork Reuters-21578 is a collection of about 20K news-lines (see reference for more information, downloads and copyright notice), structured using SGML and categorized with 672 labels. They are diveded into five main categories: Topics Places People Organizations Exchanges However, most of them are unused and, looking at the distribution, it’s possible to notice a complete … [Read more…]