Posts with #BayesianDeepLearning

#BayesianDeepLearning

Public posts on X that use #BayesianDeepLearning.

Related hashtags

  1. Philipp Becker@philippb06
    🧩 How does #BayesianDeepLearning handle the wild terrain of real-world o.o.d. data? Novel work from our student Florian Seligmann with the #WILDS 🐾 datasets: Exploring transformers, finetuning and last-layer methods while ensembling it all! #NeurIPS2023
    03121.1K
  2. Edward Dixon✓@EdwardDixon3
    We like to do a bit of #AgeEstimation @AiRigr (#DigitalForensics!). Wanting to go beyond point estimate in our regression models, BLiTZ made it surprisingly easy to start outputting distributions instead! Also @Gradio made it easy to incorporate fancy new output in our demo!
    David Praise Chukwuma Kalu @DavidPraiseKalu
    127
  3. Edward Dixon✓@EdwardDixon3
    @EdwardDixon3
    With #BayesianDeepLearning, we no longer have mere model weights - we have _distributions_ over our weights. After all, what is a model but a guess at the "model of the Gods" which would result from training over "all possible data".
    102
  4. Long & Short@LongShort_io
    Even simple Neural Networks can achieve almost 90% accuracy in predicting $BTC price movements. Working on more complex models which will be released soon... #BayesianDeepLearning
    Download
    002
  5. Alex Matthews@alexggmatthews
    @dustinvtran
    @dustinvtran For those who are at #nips2017 we will be at the #BayesianDeepLearning workshop tomorrow to discuss this work. Since the arxiv submission we have extended our analysis to the truncation style arguments. It will be great to chat with you all.
    013
  6. Hao Wang@HaoGarfield
    Check out our paper @NatureMedicine ! Definitely one of my favorite works in the past two years. We use our Bayesian Deep Learning framework to integrate low-level FMCW radar perception with high-level continuous-time BayesNet reasoning.
    114
  7. Hao Wang@HaoGarfield
    @HaoGarfield
    This allows the AI system to accurately infer whether patients are using devices such as insulin pens and inhalers on time, and whether they are doing every step correctly. Another fun fact: our system works 24/7, and it is camera-free! #MLHealth #BayesianDeepLearning @MIT_CSAIL
    102
  8. Show more posts