The phrase "a condensed network" is correct and usable in written English.
It can be used to describe a network that has been made more compact or efficient, often in a technical or scientific context.
Example: "The researchers developed a condensed network of neurons that improved the speed of information processing in the brain."
Alternatives: "a compact network" or "a streamlined network."
The purpose of this study is to investigate a condensed neural network that combines the classification speed of neural networks and the low error rate of the nearest neighbor classifier.
We compare the condensed network to a high performance neural network pattern classifier (Kohonen) and to NN in experiments on hand-printed character recognition.
This condensed network is a fast, accurate classifier of simple architecture and function: it consists of a set of generalized perceptrons that draw maximal hyperspherical boundaries centered on patterns of memory units, each circumscribing reference patterns of a single category.
In the two materials, the typical Si O-Si bandSi O-Sid 1,080, 814 and 459 cm−1 associated with the formation of a condensed silica network are present.
In all the materials, the bands around 473, 795, 1080 and 1220 cm−1 are assigned to links of (Si O Si), which is associated with the formation of a condensed silica network (Wang et al. 2005).
Network condensations are illustrated by pairs of figures (original network - condensed network) in the section on Case Studies.
The Nrp1 gene/protein that is found in these four subnetworks is also found in our condensed network.
Using the condensed network, the user can investigate components of the network where interactions, stimulations or inhibitions start up or shut down, comparing experiment E1 with E2.
The condensed network contains good candidates for interpreting the experiment in mechanistic terms, giving rise to the design of new experiments.
The condensed networks match closely, and we observe the following in both: (a) the shutdown of stimulations around the Esrrb gene; we were already able to validate full downregulation of Esrrb at 48 hours (Warsow et al. [50]), and (b) the startup of interactions around the transcriptional co-repressor TRIM28 (also known as TIF1beta); one of its repressed targets is Stat3.
