Faster R-CNN: Down the rabbit hole of modern object detection
Previously, we talked about object detection, what it is and how it has been recently tackled using deep learning. If you haven’t read our previous blog post, we suggest you take a look at it before continuing. Last year, we decided to get into Faster R-CNN, reading the original paper, and all the referenced papers (and so on and on) until we got a clear understanding of how it works and how to implement it.
Deep Learning for NLP: Advancements & Trends
Over the past few years, Deep Learning (DL) architectures and algorithms have made impressive advances in fields such as image recognition and speech processing. Their application to Natural Language Processing (NLP) was less impressive at first, but has now proven to make significant contributions, yielding state-of-the-art results for some common NLP tasks. Named entity recognition (NER), part of speech (POS) tagging or sentiment analysis are some of the problems where neural network models have outperformed traditional approaches.
Our ODSC talks in video
As we previously announced, the last couple of weeks we’ve been launching Luminoth, our brand new open source toolkit for Computer Vision. As part of this launch, we gave talks in the Open Data Science Conference (ODSC), both at the London and San Francisco editions. The events were a great success, as in 5 days they accumulated around 5000 data scientists, while hosting more than 200 talks from renowned people in the academia and industry.
Launching Luminoth: our open source computer vision toolkit
After a few months working in stealth mode, we are very proud to launch our Deep Learning initiative: luminoth.ai Luminoth is an open source toolkit for computer vision. Currently, we support object detection and image classification, but we are aiming for much more. It is built in Python, using Google’s Machine Intelligence framework, TensorFlow; and Sonnet, a very useful library built by DeepMind for building complex neural networks with reusable components.
We'll be speaking at ODSC San Francisco & London, presenting our Deep Learning R&D findings
As we have become accustomed to, exciting things are happening in the Machine Learning ecosystem. One can easily argue that it is novel applications of Deep Learning which are leading this excitement. Real world uses of Deep Learning are growing day to day: improving machine text translation, music generation, style transfer, object detection and cooler than ever generative models are just a few examples. The vast number of new applications, and the pace of improvement over existing ones, make it harder than ever to keep up to date with the latest advancements in the field.
Object Detection with Deep Learning: The Definitive Guide
There’s no shortage of interesting problems in computer vision, from simple image classification to 3D-pose estimation. One of the problems we’re most interested in and have worked on a bunch is object detection. Like many other computer vision problems, there still isn’t an obvious or even “best” way to approach object detection problems, meaning there’s still much room for improvement. In this post, we’ll do a quick rundown of the most common problems in object detection, go into the details of practical applications and understand how the way to tackle it has been shifting in the last years with deep learning.
Finding the right representation for your NLP data
When considering what information is important for a certain decision procedure (say, a classification task), there’s an interesting gap between what’s theoretically —that is, actually— important on the one hand and what gives good results in practice as input to machine learning (ML) algorithms, on the other. Let’s look at sentiment analysis tools as an example. Expression of sentiment is a pragmatic phenomenon. To predict it correctly, we need to know both the meaning of the sentences and the context in which those sentences appeared.
Magazine: A collection of our Machine Learning articles - Get a copy!
Hello everybody, exciting news here: we released our first Machine Learning magazine. We all know it. Machine Learning is undoubtedly one of the most relevant fields in Computer Science and beyond. One can easily state, looking at some data, that this field is now the talk of the town and that we are all somehow touched by it. Although we are all increasingly learning about how Machine Learning – subfield of AI – is changing our day to day, sometimes we might lack some knowledge on how Machine Learning actually works.
List of Machine Learning / Deep Learning conferences in 2019
There’s a record amount of exciting Machine Learning (ML) and Deep Learning conferences worldwide and keeping track of them may prove to be a challenge. This list provides an overview with upcoming ML conferences and should help you decide which one to attend, sponsor or submit talks to. For some conferences we added remarkable speakers and discount codes. Those with the tag “Tryolabs’ Pick” indicate our personal favorites. Drop us a line here if you think of a conference that should be added to the list.
Pandas & Seaborn - A guide to handle & visualize data in Python
Last Updated: July 2018 Here at Tryolabs we love Python almost as much as we love machine learning problems. These kind of problems always involve working with large amounts of data which is key to understand before applying any machine learning technique. To understand the data, we need to manipulate it, clean it, make calculations and see how variables behave independently, and how they relate to one another. At this post will show how we have been doing this lately.