Recently I have found some interesting papers and analysis about the issue of semantic synthesis and segmentation used both for natural language processing and for advanced computer vision imaging. I tended to be skeptical of this use of the word 'semantic', but then I realized that within the field of computer science, the term is … Continue reading Paper with Code Series: Semantic Image Synthesis with Spatially-Adaptive Normalization
Computer Science
A conversation on AI from MIT Artificial General Intelligence Lectures
The Massachusetts Institute of Technology (MIT) has been given a series of lectures titled MIT 6.S099: Artificial General Intelligence. It is part of the syllabus of a course on Artificial General Intelligence and Deep Learning delivered by Lex Fridman. It featured a series of conversations with some prominent researchers in the fields of machine learning, … Continue reading A conversation on AI from MIT Artificial General Intelligence Lectures
Sequence to sequence learning with Convolutional Neural networks
A team of researchers from Facebook AI research released an interesting paper about sequence to sequence learning with convolutional neural networks (CNNs). CNNs has been mainly used in computer vision implementations, being a state-of-the-art stack for the the researche and development in object recognition or image recognition. Less often have CNNs been implemented for machine … Continue reading Sequence to sequence learning with Convolutional Neural networks
How to train, deploy and develop TensorFlow AI Models, SparkML from Jupyter Notebook to production
Today I would like to post a more technical and pure engineering topic. The heart of the matter in Artificial Intelligence(AI) is more practical/empirical based than theoretical. Even though the conceptual framework is undoubtedly important. But to get a good grasp of the real work involved in setting up all the apparatus for a … Continue reading How to train, deploy and develop TensorFlow AI Models, SparkML from Jupyter Notebook to production
Success with deep learning architectures, surrogate random matrices and spectral ergodicity
From now and then I just wonder how good my social media connections really are. Often crossed my mind that social media is more noise than signal, real good signals of the best we can be and do as human beings. There is a lot of not that good about what human beings should be … Continue reading Success with deep learning architectures, surrogate random matrices and spectral ergodicity
PyData London 2017: Bayesian Deep Learning talk by Andrew Rowan
Today I could not but come back again to PyData London 2017 series of YouTube videos. That is because the field of Bayesian Deep Learning continues to make its strides forward, but also because the quality of the research, researchers and speakers on the subject deserves mine and yours attention, please... 😊 This time the culprit … Continue reading PyData London 2017: Bayesian Deep Learning talk by Andrew Rowan
Recommender systems with TensorFlow
Guillaume Allain gave an interesting talk at the recent PyData London 2017 event. It was about the implementation of recommender systems using TensorFlow. The talk is shared in the YouTube video below. I recommend the reader to also fork the GitHub pull request/repository Tensorflow-based Recommendation systems, where a detailed description of this developement is available as well as all … Continue reading Recommender systems with TensorFlow
Ensembles of Neural Networks: Train 1, get M for free
I am coming back to reviewing a paper that I deem relevant or with some probable line of further research that may prove worth to pursue in the future about deep neural networks. I was parsing one of O'Reilly Artificial Intelligence latest newsletter, and I found the paper below about ensembles of neural networks. It … Continue reading Ensembles of Neural Networks: Train 1, get M for free
Generalization and Equilibrium in Generative Adversarial Nets (GANs) – a talk by Sanjeev Arora
It has been a while after I reviewed my last paper here for The Intelligence of Information. Â I've been posting YouTube videos with my own comments and interpretations of what I see and hear, and as a matter of fact it has been rewarding and a somewhat more interactive way to present the topics this … Continue reading Generalization and Equilibrium in Generative Adversarial Nets (GANs) – a talk by Sanjeev Arora
TensorFlow Dev Summit 2017: Integrating Keras and TensorFlow
I am briefly sharing a video from the last TensorFlow Dev Summit in February 2017. My choice has fallen to a presentation by François Chollet of the deep learning library API Keras and its integration with TensorFlow. As Dr. Chollet explains, Keras integrated with TensorFlow promises to streamline deep learning frameworks in ways that will … Continue reading TensorFlow Dev Summit 2017: Integrating Keras and TensorFlow