Software for Artificial Minds

Giuseppe Bonaccorso

Artificial Intelligence, Machine Learning, Deep Learning, Data Science, Philosophy of Mind

  • Home
  • Resume / CV
  • Blog
  • Bonaccorso’s Law
  • Essays in Italian
  • Contact
  • Hire me
  • Testimonials
  • Gallery
  • Disclaimer

tensorflow

Hetero-Associative Memories for Non Experts: How “Stories” are memorized with Image-associations

12/31/2017 / 4 Comments

Think about walking along a beach. The radio of a small kiosk-bar is turned-on and a local DJ announces an 80’s song. Immediately, the image of a car comes to your mind. It’s your first car, a second-hand blue spider. While listening to the same song, you drove your girlfriend to the beach, about 25 … [Read more…]

Posted in: Artificial Intelligence, Computational Neuroscience, Convnet, Deep Learning, Generic, Machine Learning, Neural networks, Philosophy of Mind, Tensorflow, Tensorflow Tagged: autoencoder, brain, deep learning, heteroencoder, machine learning, mind, tensorflow

ML Algorithms Addendum: Fisher Information

09/02/2017 / Leave a Comment

Fisher Information, named after the statistician Ronald Fisher, is a very powerful tool in both Bayesian Statistics and Machine Learning. To understand its “philosophical” meaning, it’s useful to think about a simple classification task, where our task is to find a model (characterized by a set of parameters) that is able to reproduce the data … [Read more…]

Posted in: Artificial Intelligence, Machine Learning, Machine Learning Algorithms Addenda, Python, Tensorflow Tagged: information theory, machine learning, statistical learning, tensorflow

Twitter Sentiment Analysis with Gensim Word2Vec and Keras Convolutional Networks

08/07/2017 / 18 Comments

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…]

Posted in: Convnet, Deep Learning, Generic, Keras, Neural networks, NLP, Python, Tensorflow Tagged: convnet, keras, nlp, sentiment analysis, tensorflow, twitter

SVD Recommendations using Tensorflow

08/02/2017 / 4 Comments

Recommendation system based on the user-item matrix factorization have become more and more important thanks to powerful and distributable algorithms like ALS, but sometimes the number of users and/or items is not so huge and the computation can be done using directly a SVD (Singular Value Decomposition) algorithm. In this post, we’re going to discuss … [Read more…]

Posted in: Machine Learning, Python, Tensorflow Tagged: recommendations, svd, tensorflow

Lossy image autoencoders with convolution and deconvolution networks in Tensorflow

07/29/2017 / 4 Comments

Fork Autoencoders are a very interesting deep learning application because they allow a consistent dimensionality reduction of an entire dataset with a controllable loss level. The Jupyter notebook for this small project is available on the Github repository: https://github.com/giuseppebonaccorso/lossy_image_autoencoder. The structure of a generic autoencoder is represented in the following figure: The encoder is a function … [Read more…]

Posted in: Convnet, Deep Learning, Neural networks, Python, Tensorflow Tagged: autoencoder, cifar, convnet, tensorflow

Machine Learning Algorithms

07/23/2017 / 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…]

Posted in: Keras, Machine Learning, Python, Scikit-Learn, Tensorflow Tagged: book, keras, machine learning, nlp, nltk, python, scikit-learn, tensorflow

Keras-based Deepdream experiment based on VGG19

07/09/2017 / 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…]

Posted in: Convnet, Deep Learning, Keras, Machine Learning, Python, Tensorflow, Tensorflow, Theano Tagged: convnet, deepdream, keras, tensorflow, theano

Keras-based Neural Artistic Style Transfer

05/17/2017 / 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. See also: Neural artistic style transfer experiments with Keras – Giuseppe Bonaccorso Artistic style transfer using neural networks is a technique proposed by Gatys, Ecker and Bethge in … [Read more…]

Posted in: Artificial Intelligence, Convnet, Deep Learning, Keras, Machine Learning, Neural networks, Python, Tensorflow, Theano Tagged: convnet, deep learning, github, image, keras, python, tensorflow, theano

Social

  • View giuseppe.bonaccorso’s profile on Facebook
  • View GiuseppeB’s profile on Twitter
  • View giuseppebonaccorso’s profile on Instagram
  • View gbonaccorso’s profile on Pinterest
  • View giuseppebonaccorso’s profile on LinkedIn
  • View giuseppebonaccorso’s profile on GitHub
  • View UClcSc-gn6dHmW5LXver8lYQ’s profile on YouTube
  • View +GiuseppeBonaccorso’s profile on Google+

Search articles

Latest blog posts

  • Fundamentals of Machine Learning with Scikit-Learn 03/22/2018
  • Getting Started with NLP and Deep Learning with Python 02/26/2018
  • Hetero-Associative Memories for Non Experts: How “Stories” are memorized with Image-associations 12/31/2017
  • A glimpse into the Self-Organizing Maps (SOM) 10/22/2017
  • ML Algorithms addendum: Passive Aggressive Algorithms 10/06/2017

Subscribe to this blog

Join 2,183 other subscribers

Machine Learning Algorithms Addenda

Follow me on Twitter

My Tweets

Copyright © 2006-2018 Giuseppe Bonaccorso. All Rights Reserved   Privacy Policy - Cookie Policy

The articles hosted in this website are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.