back
user profile
brandonb
9,345karma·1,335submissions·January 17, 2011
about
Data for good.
Co-Founder at Empirical Health (https://empirical.health). Don't die of heart disease.
Before: Co-Founder @ Cardiogram (ML for heart health)
CTO at Sift Science (YC S11, machine learning to fight fraud)
Data Science @ UCSF Cardiology
HealthCare.gov rescue team
Google (Android speech recognition, search ads ML)
brandonb.cc
recent activity (1,335 total)
comment
Interesting idea! I think this is analogous to the idea of a de-noising autoencoder in computer vision. Here, instead of introducing Gaussian noise at the pixel level and using a CNN, you're intr…
comment
Well, I guess my sincerity detector is officially broken, huh?
comment
This seems like a sincere comment, so in case it's helpful, here's my interpretation of why others may be downvoting it. Deep learning practitioners are aware that they're using non-con…
comment
As context, this is Apple's first published AI research paper. After Russ Salakhutdinov was hired, he promised that Apple would start publishing AI papers in peer-reviewed conferences... and this…
comment
In our case, we're applying deep learning to sensor data, so much of the day-to-day work of a machine learning engineer is experimenting with new neural architectures rather than feature engineer…
comment
I agree--the impact of a great engineer working in healthcare is very high, particularly if you partner with medical experts. We're a small startup that has partnered with UCSF Cardiology to dete…
comment
One company that does this is Forter: https://www.forter.com/
comment
Your mocks look really nice! If you're interested in the fraud problem, you might try some of the other fraud detection startups, like Sift Science (which you mention), Forter, Riskified, or Sign…
comment
Good question. Atrial fibrillation is the first clinical application, and my hope is that we'll have final publishable results in early 2017. Other studies have shown is that, in a population at …
comment
Thanks for posting endswapper! I'm one of the co-founders of Cardiogram. If anybody has questions about either Cardiogram Apple Watch app or the science behind it, happy to talk here.
comment
I hear this sentiment a lot, and don't entirely disagree with it... but it oversimplifies our community massively. If you want to work on big, meaningful problems, here are some compelling option…
comment
Very cool! I've worked with the Insight Health Data fellows before, enjoyed the experience, and they got a lot done. I think one thing that's tricky about artificial intelligence as a field …
comment
One way to think about AI's potential impact is less about replacing what physicians do well currently, and more about doing things they can't do at all. Take ECGs -- it's true that in …
comment
Yep—as you point out, the first paragraph of the article cites the same 1979 MYCIN accuracy results you did. My criteria for success is enduring impact on the way medicine is practiced, so the the res…
comment
This is an insightful response! I'm curious, what AI application are you working on?
comment
What makes you skeptical about dissemination of your product in particular?
comment
I read your question a few times but I'm sorry, I still don't understand. Can you rephrase it?
comment
There are lots of parallels to fraud detection! Label imbalance is the obvious one: in both cases, you're looking for the proverbial needle in the haystack, so techniques like anomaly detection o…
comment
What's strange is that although doctors have been reluctant to adopt AI like MYCIN, the pace of adoption for other innovations like new surgeries, drugs, and implantable devices is actually quite…