Edited, memorised or added to reading queue

on 07-Jul-2025 (Mon)

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

(L-DNN), were inspired by brain neurophysiology. These deep learning algorithms separate feature training and rule training and are able to add new rule information on the fly.

While they still learn features slowly using a large and balanced data set, L-DDNs don't learn rules at this stage. And they don't need images of all known valve defects—the dataset can be relatively generic as long as the objects possess similar features (such as curves, edges, surface properties). With L-DNNs, this part of model creation can be done once, and without the help of the manufacturers.

What our hypothetical valve manufacturer needs to know is this: After the first step of feature learning is completed, they need only provide a small set of images of good valves for the system to learn a set of rules that define a good valve. There's no need to provide any images of defective valves. L-DNNs will learn on a single presentation of a small dataset using only “good" data (in other words, data about good ventilator valves), and then advise the user when an atypical product is encountered. This method is akin to the process humans use to spot differences in objects they encounter every day—an effortless task for us, but a very hard one for deep learning models until L-DNN systems came along.

statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

Deep Learning Has Reinvented Quality Control in Manufacturing—but It Hasn’t Gone Far Enough AI systems that make use of “lifelong learning” techniques are more flexible and faster to train
These so-called continual or lifelong learning systems, and in particular lifelong deep neural networks (L-DNN), were inspired by brain neurophysiology. These deep learning algorithms separate feature training and rule training and are able to add new rule information on the fly. While they still learn features slowly using a large and balanced data set, L-DDNs don't learn rules at this stage. And they don't need images of all known valve defects—the dataset can be relatively generic as long as the objects possess similar features (such as curves, edges, surface properties). With L-DNNs, this part of model creation can be done once, and without the help of the manufacturers. What our hypothetical valve manufacturer needs to know is this: After the first step of feature learning is completed, they need only provide a small set of images of good valves for the system to learn a set of rules that define a good valve. There's no need to provide any images of defective valves. L-DNNs will learn on a single presentation of a small dataset using only “good" data (in other words, data about good ventilator valves), and then advise the user when an atypical product is encountered. This method is akin to the process humans use to spot differences in objects they encounter every day—an effortless task for us, but a very hard one for deep learning models until L-DNN systems came along. Rather than needing thousands of varied images, L-DNNs only require a handful of images to train and build a prototypical understanding of the object. The system can be deployed in seco




Flashcard 7713904790796

Tags
#deep-learning #keras #lstm #python #sequence
Question
When a network is fit on [...] data that has a range of values (e.g. quantities in the 10s to 100s) it is possible for large inputs to slow down the learning and convergence of your network, and in some cases prevent the network from effectively learning your problem.
Answer
unscaled

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
When a network is fit on unscaled data that has a range of values (e.g. quantities in the 10s to 100s) it is possible for large inputs to slow down the learning and convergence of your network, and in some cases prevent

Original toplevel document (pdf)

cannot see any pdfs