Top all-time · #11767
Alex Kendall
Personal blog · alexgkendall.com/computer_visionaiscience
Alex Kendall's personal blog at alexgkendall.com covers ai and science. Since 2017, 6 different Hacker News readers have linked it 6 times, most often “Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI”. No feed was found, so read it on the site itself.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
HN readers link Alex Kendall's posts on Bayesian deep learning and model uncertainty, covering how a model's stated confidence can help a doctor decide, and 3D scene sensing and learning.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Alex Kendall — Wayve Co-founder and CEO. Building Embodied AI for autonomous driving.
Most-linked posts?
- /computer_vision/bayesian_deep_learning_for_safe_ai/2 people · 2 mentions · first linked 2019-05-09
- Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI2 people · 2 mentions · first linked 2017-05-23
What Hacker News says?
> Say the model outputs 90% chance of nothing, 10% chance of a deadly condition that needs to be investigated ASAP. Doctors are often overworked and tired and can miss it. Knowing where the certainties and uncertainties of the model lies would allow the doctor to compare that to its own training "Ah but it didn't at all judge based on X and Y" and limit decision machine based on "trusting the algorithms". Spot on. P…
Comment linking /computer_vision/bayesian_deep_learning_for_safe_ai/
on “The Case for Bayesian Deep Learning”Submitted Have We Forgotten about Geometry in Computer Vision? as a story · 406 points
HN discussionDon't think it's exactly what you're talking about (I'm sure there are other works much closer to what you have in mind, just can't recall off the top of my head) — but you might find PoseNet ( https://www.cv-foundation.org/openaccess/content_iccv_2015/p... ) interesting. Not explicitly 3D, but estimates where in a large-scale scene a picture was taken using an end-to-end convolutional network. With that said, I thi…
Comment linking /computer_vision/have_we_forgotten_about_geometry_in_computer_vision
on “Beyond the pixel plane: sensing and learning in 3D”Submitted Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI as a story · 4 points
HN discussionVery interesting paper. With some surprising insights (need to read it a couple more times for sure). The conclusion states: > Overall, attaining models that are robust and interpretable will require explicitly > encoding human priors into the training process. I feel that is true, though another part of the solution IMO lies in coming up with classifiers that can do more than output a probability alone. I agree tha…
Comment linking /computer_vision/bayesian_deep_learning_for_safe_ai/
on “Adversarial Examples Are Not Bugs, They Are Features”Submitted Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI as a story · 3 points
HN discussion