A survey of deep active learning
Active learning (AL) attempts to maximize a model's performance gain while annotating the
fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount …
fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount …
A survey on active learning and human-in-the-loop deep learning for medical image analysis
Fully automatic deep learning has become the state-of-the-art technique for many tasks
including image acquisition, analysis and interpretation, and for the extraction of clinically …
including image acquisition, analysis and interpretation, and for the extraction of clinically …
[图书][B] Designing machine learning systems
C Huyen - 2022 - books.google.com
Machine learning systems are both complex and unique. Complex because they consist of
many different components and involve many different stakeholders. Unique because …
many different components and involve many different stakeholders. Unique because …
[图书][B] Machine learning with quantum computers
M Schuld, F Petruccione - 2021 - Springer
The introduction gives some context about what quantum machine learning is, how it got
established as a sub-discipline of quantum computing and which higher level approaches …
established as a sub-discipline of quantum computing and which higher level approaches …
Weakly supervised machine learning
Supervised learning aims to build a function or model that seeks as many mappings as
possible between the training data and outputs, where each training data will predict as a …
possible between the training data and outputs, where each training data will predict as a …
High accuracy and high fidelity extraction of neural networks
In a model extraction attack, an adversary steals a copy of a remotely deployed machine
learning model, given oracle prediction access. We taxonomize model extraction attacks …
learning model, given oracle prediction access. We taxonomize model extraction attacks …
Machine learning & artificial intelligence in the quantum domain: a review of recent progress
V Dunjko, HJ Briegel - Reports on Progress in Physics, 2018 - iopscience.iop.org
Quantum information technologies, on the one hand, and intelligent learning systems, on the
other, are both emergent technologies that are likely to have a transformative impact on our …
other, are both emergent technologies that are likely to have a transformative impact on our …
PRADA: protecting against DNN model stealing attacks
Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality
of ML models becomes paramount for two reasons:(a) a model can be a business …
of ML models becomes paramount for two reasons:(a) a model can be a business …
Stealing machine learning models via prediction {APIs}
Machine learning (ML) models may be deemed confidential due to their sensitive training
data, commercial value, or use in security applications. Increasingly often, confidential ML …
data, commercial value, or use in security applications. Increasingly often, confidential ML …