Mail Processing with Deep Learning: A Case Study
Businesses increasingly delegate simple, boring, and repetitive tasks to artificial intelligence. In a case study, Alexandre Hubert — lead data scientist of software company Dataiku’s U.K. operations — worked on a team of three to automate mail processing with deep learning. At ODSC Europe 2018, Hubert detailed how his team... Read more
Efficient, Simplistic Training Pipelines for GANs in the Cloud with Paperspace
Generative adversarial networks — GANs for short — are making waves in the world of machine learning. Yann LeCun, a legend in the deep learning community, said in a Quora post “ the most interesting idea in the last 10 years in .” GANs (and, more generally,... Read more
Why are Convnets Often Better Than the Rest? Part III
This is the third part in a series on Convnets. Read the first part here and the second part here. Shared weights The shared weight design is exactly why convolutional nets (Convnets for short) are good at detecting the same features in different parts of an image. When I mentioned shared... Read more
Getting to Know Keras for New Data Scientists
For many new data scientists transitioning into AI and deep learning, the Keras framework is an efficient tool. Keras is a powerful and easy-to-use Python library for developing and evaluating deep learning models. In this article, we’ll lay out the welcome mat to the framework. You should walk away with... Read more
Note: All images below are used with permission from Chalk Dust Magazine. Please see their article here. Using machine learning to play games has always been an excellent way to understand and evolve learning models. In the last ten years, Google DeepMind managed to train a convolutional neural network... Read more
Data Storage Keeping Pace for AI and Deep Learning
Data is the new currency driving accelerated levels of innovation powered by AI. Enterprises require modern data storage architectures purpose-built for deep learning and designed to shorten the time to insights while simplifying complex big data pipelines. Continuing to use legacy storage systems, however, will introduce serious complications in... Read more
Overview of the YOLO Object Detection Algorithm
Let’s review the YOLO (You Only Look Once) real-time object detection algorithm, which is one of the most effective object detection algorithms that also encompasses many of the most innovative ideas coming out of the computer vision research community. Object detection is a critical capability of autonomous vehicle technology.... Read more
Deep Learning Question-Answer Model with Demo
  How amazing would be a model that can answer questions from any paragraph by extracting word(s) from the paragraph that are most relevant. Deep learning has made this possible! See below a demo for such a question-answer super model. In this demo you can put in any context up to 300 words... Read more
Why are Convnets Often Better Than the Rest? Part II
The Weakness of Traditional Neural Networks, as opposed to Convnets Following on Part I of “Why are Convnets often Better than the Rest?”, we will now look at a traditional neural network’s weakness. As before, I am going to assume you understand the basics of neural network modeling already,... Read more
Lessons Learned and Reinforced from Writing My Own Deep Learning Package
At work, I’ve been rolling my own deep learning package to experiment with graph convolutional neural networks. I did this because in graph-centric deep learning, an idea I picked up from this paper, the inputs, convolution kernels, and much more, are being actively developed, and the standard APIs don’t... Read more