Last week, I went to work on a machine learning example that used the ever popular ImageNet dataset. It’s the classic image classification problem known by every machine learning practitioner at this point. Here’s an image, classify which of the 1,000 categories it fits in.

But I noticed something strange about it this time. First the website went down and when it came back up, everything had changed.

I didn’t think much of it until I realized that the download hashes were different and accuracies for the models were slightly off. …

“Move fast, think even faster,” is the ultimate goal of data science.

We all want our AI models to do predictions faster and better than we can do them ourselves. Even more, we want to develop those models at lightspeed. But the reality is often a lot different. Running experiments, comparing results, deploying models and monitoring them is not fast or efficient. It’s a slow, tedious, and time consuming.

If we want to speed up the time it takes to get a model from idea to inference we’ve got to get better at performing more experiments faster. …

The key to building powerful machine learning models is learning “the right things from the right data.” Just as we humans constantly take in new information and update what we think about the world, ML models must continually learn from new data to keep their insights sharp and relevant. Continuous improvement is utterly crucial if you expect your model to work in the real world.

Breast cancer is a horrible disease that affects millions worldwide. In the US and other high-income countries, advances in medicine and increased awareness have significantly improved the survival rate of breast cancer to 80% or higher. However, in many lower-income countries the survival rate is below 40%, largely due to a lack of early detection systems.¹

Advances in AI and medicine can make massive differences in beating diseases like breast cancer by extending diagnostics, enhancing pattern recognition in imaging, and deploying these resources for those who need them most.

One promising advancement for early detection breast cancer systems is the…

I’ve been building machine learning and data processing pipelines with Pachyderm for a while now. It’s an incredibly powerful platform, but as with most things, there are some “gotchas” along the way. I sadly learned all of these lessons the hard way, but hopefully I can help others avoid the pain through some of these tips and work-arounds.

A comprehensive resource for deep learning in natural language processing and speech recognition.

I am extremely excited to announce the availability of our textbook: Deep Learning for NLP and Speech Recognition!

Deep learning has quickly become a foundational technique in almost every AI and machine learning application. The ability to learn complex concepts directly from data and achieve much higher accuracies have rocketed it to one of the most popular research areas in technology. When my colleagues and I began putting this book together, we noticed that there wasn’t a single resource that covered the modern deep learning approaches in…