Presented By O’Reilly and Intel AI
Put AI to work
Sep 4-5, 2018: Training
Sep 5-7, 2018: Tutorials & Conference
San Francisco, CA

Debuggable deep learning

Avesh Singh (Cardiogram), Kevin Wu (Cardiogram)
1:45pm-2:25pm Thursday, September 6, 2018
Implementing AI
Location: Yosemite BC
Secondary topics:  Deep Learning models, Health and Medicine
Average rating: *****
(5.00, 1 rating)

Who is this presentation for?

  • Engineers and researchers

Prerequisite knowledge

  • A basic understanding of neural networks, including forward and backpropagation, recurrent neural networks, and convolutional neural networks
  • No medical knowledge required

What you'll learn

  • Learn how to apply your intuitions on properties of your data to come up with model architectures and generate hypotheses for problems in the modeling process
  • Explore debugging techniques for deep neural networks, such as analysis of gradients and network activations, and querying the neural network with different inputs, using TensorBoard for visualizations along with synthetic or heuristic prediction tasks


Although deep neural networks have shown high accuracy in fields like computer vision, natural language processing, and medicine, they often behave like black boxes. Avesh Singh and Kevin Wu explain the intuitions that went into building DeepHeart, a DNN that detects cardiovascular disease from heart rate data. Next, they explain techniques to debug DNNs, including visualizing activations and training on synthetic data. Avesh and Kevin also analyze gradients for recurrent neural networks, looking for ways to quantify the amount of information loss a network may be experiencing over time. You’ll leave this talk with a greater understanding of how to design and debug a deep neural network for your machine learning task.

Photo of Avesh Singh

Avesh Singh


Avesh Singh is an engineer at Cardiogram, a startup that applies deep learning to wearable data. Previously, Avesh worked at Nest Labs and Google. He holds a a BS and MS in computer science from Carnegie Mellon University.

Photo of Kevin Wu

Kevin Wu


Kevin Wu is an engineer at Cardiogram, a startup that applies deep learning to wearable data. Previously, Kevin worked at Two Sigma and Credit Suisse. He holds a BS and MS in computer science from Stanford University.