Creativity Inspired Zero-shot Learning
Zero-shot learning (ZSL) aims at understanding unseen categories with no training examples from class-level descriptions. To improve the discriminative power of zero-shot learning, we model the visual learning process of unseen categories with inspiration from the psychology of human creativity for producing novel art. We relate ZSL to human... Read more
Generative Adversarial Networks for Finance
Financial instruments like options and futures have been around for more than two centuries. Although they became quite notorious during the 2008 stock market turmoil, they serve a real economic purpose for companies around the world. To explain financial... Read more
Automating Image Annotation with MAX
This blogpost introduces a use-case example to automate image annotation with MAX (Model Asset Exchange). To learn more about how our deep learning models are created, containerized, and deployed to production, come join our training at ODSC West 2019: Deploying Deep Learning Models as Microservices.  Introduction The Model Asset Exchange... Read more
Three Methods of Data Pre-Processing for Text Classification
Editor’s Note: Nick will be presenting on this idea of data pre-processing during the workshop “Choosing The Right Deep Learning Framework: A Deep Learning Approach,” at ODSC Europe in London this November! As a developer advocate at IBM, I work to empower AI, machine learning, and deep learning developers... Read more
Composable Machine Learning
Even as machine learning (ML) algorithms become more sophisticated and powerful, the way ML teams build ML systems hasn’t changed much. In this article, we’ll explain the need for composable machine learning systems. First, take a look at the old, inefficient way. Once the team figures out the task... Read more
Applications of AI in Cybersecurity
Editor’s Note: See Dustin’s talk “Applications of AI in Cybersecurity” at ODSC West 2019. Security has historically lagged behind the implementation of new technology. With AI/ML transforming how industries and government agencies do business and serve citizens, it is critical that developers build security into our architectures from the... Read more
A Crash Course on Deep Learning in the Cloud
Deep learning is the newest area of machine learning and has become ubiquitous in predictive modeling. The complex brain-like structure of deep learning models is used to find intricate patterns in large volumes of data. They have substantially improved the performance of general supervised models, time series, speech recognition,... Read more
It’s About Time. Designing a Streaming Architecture For High Frequency Sensor Data
Time is precious, short, relative and complicated… especially when managing streaming applications, where calculations are performed in near-real-time. Even more challenges arise when data come from sensors and are sampled at different rates and high frequencies. Machine and deep learning algorithms are often incorporated and have different mathematical assumptions... Read more
ODSC West 2019 Preview: Get Started with Deep Learning (by Trying It!)
There are lots of ways to get started learning deep learning. The best we’ve found is to dive in with examples!  If you’re attending ODSC West, you can get your hands dirty at the 1.5-hour workshop: Practical Deep Learning. Bring your laptop for hands-on examples training a deep learning... Read more
Sequence Modelling with Deep Learning
This is a short preview post for my upcoming tutorial  “Sequence Modelling with Deep Learning” at ODSC London in November 2019. — Much of data is sequential — think speech, text, DNA, stock prices, financial transactions, and customer action histories. Our best-performing methods for modelling sequence data use deep neural networks,... Read more