Fast and three-rious: Speeding up weak supervision with triplet methods
Weak supervision is a popular method for building machine learning models without relying
on ground truth annotations. Instead, it generates probabilistic training labels by estimating …
on ground truth annotations. Instead, it generates probabilistic training labels by estimating …
Shoring up the foundations: Fusing model embeddings and weak supervision
Foundation models offer an exciting new paradigm for constructing models with out-of-the-
box embeddings and a few labeled examples. However, it is not clear how to best apply …
box embeddings and a few labeled examples. However, it is not clear how to best apply …
Train and you'll miss it: Interactive model iteration with weak supervision and pre-trained embeddings
Our goal is to enable machine learning systems to be trained interactively. This requires
models that perform well and train quickly, without large amounts of hand-labeled data. We …
models that perform well and train quickly, without large amounts of hand-labeled data. We …
The AI-Native Software Development Lifecycle: A Theoretical and Practical New Methodology
C Hymel - arXiv preprint arXiv:2408.03416, 2024 - arxiv.org
As AI continues to advance and impact every phase of the software development lifecycle
(SDLC), a need for a new way of building software will emerge. By analyzing the factors that …
(SDLC), a need for a new way of building software will emerge. By analyzing the factors that …
The impact of GitHub Copilot on developer productivity from a software engineering body of knowledge perspective
Recent times saw captivating improvements to artificial intelligence-assisted code
completion technology. The precise effect this contributes to conventional software …
completion technology. The precise effect this contributes to conventional software …
[图书][B] Label-Efficient Machine Learning for Medical Image Analysis
SMI Hooper - 2023 - search.proquest.com
Medical imaging is an essential tool in healthcare, and radiologists are highly trained to
detect and characterize disease in medical images. However, relying solely on human …
detect and characterize disease in medical images. However, relying solely on human …
A Vision on Accelerating Enterprise IT System 2.0
The proliferation of commodity based big data platforms and an exponential increase in the
research in machine learning techniques lead to a change in application development …
research in machine learning techniques lead to a change in application development …
[PDF][PDF] Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision (Supplementary material)
Weak supervision is a broad set of techniques using weak sources of signal to supervise
models, such as distant supervision [Takamatsu et al., 2012], co-training methods [Blum and …
models, such as distant supervision [Takamatsu et al., 2012], co-training methods [Blum and …