Contributions to Deep Learning Models - RiuNet
... Graphical representation of DNN model with two hidden layers. . . .
The Backpropagation algorithm for a neural network with two hidden
layers. Note that bias terms have been ommited for simplicity. . . . .
Architecture of LeNet-5, a convolutional neural network for handwritten digits recognition. . ...
Finding Non-Redundant, Statistically Signi cant Regions in
... depends critically on difficult to set parameter values.
A second problem for the most previous approaches is that
they assume, explicitly or implicitly, that clusters have some
point density controlled by user-defined parameters, and
they will (in most cases) report some clusters. However,
we have ...
Cluster Analysis for Large, High
... subdivided. In addition, the clustering solution was proved to be robust in the presence of
noise in moderate levels, and when the clusters are partially overlapping.
In the second part of the thesis, a novel method for generating synthetic datasets
with variable structure and clustering difficulty ...
Aalborg Universitet
... simple models such that it is technically possible and economically affordable for domain experts to build and maintain these models. If expert systems should ever reach a wider audience, we see this simplicity as a prerequisite. In general we might summarize the benefits of this approach as
follows ...
g1020_ww9_aap
... A Degraded Second outcome occurs for a block of packets observed during a 1 second interval
when the ratio of lost packets at the egress UNI to total packets in the corresponding second interval
at the ingress UNI exceeds D%. Sequence numbers and time stamps contained in packet headers
may be used t ...
The DL-Lite Family - Dipartimento di Informatica e Sistemistica
... efficient, i.e., worst-case polynomial time, reasoning algorithms lack
modeling power required in capturing conceptual models and basic ontology languages, while most DLs with sufficient modeling power suffer
from inherently worst-case exponential time behavior of reasoning [5, 6].
Although the requ ...
Risk Analysis for the Artificial General Intelligence Research and
... For risk analysis, important questions concern the probabilities, timings, and consequences of the
invention of key ASI technologies. Regarding the consequences, Yudkowsky (2008), Chalmers
(2010) and others argue that ASIs could be so powerful that they will essentially be able to do
whatever they c ...
Prototype-based Classification and Clustering
... partitioning approaches are not always appropriate for the task at hand, especially if the groups of data points are not well separated, but rather form
more densely populated regions, which are separated by less densely populated ones. In such cases the boundary between clusters can only be drawn
w ...
Mixture model
In statistics, a mixture model is a probabilistic model for representing the presence of subpopulations within an overall population, without requiring that an observed data set should identify the sub-population to which an individual observation belongs. Formally a mixture model corresponds to the mixture distribution that represents the probability distribution of observations in the overall population. However, while problems associated with ""mixture distributions"" relate to deriving the properties of the overall population from those of the sub-populations, ""mixture models"" are used to make statistical inferences about the properties of the sub-populations given only observations on the pooled population, without sub-population identity information.Some ways of implementing mixture models involve steps that attribute postulated sub-population-identities to individual observations (or weights towards such sub-populations), in which case these can be regarded as types of unsupervised learning or clustering procedures. However not all inference procedures involve such steps.Mixture models should not be confused with models for compositional data, i.e., data whose components are constrained to sum to a constant value (1, 100%, etc.). However, compositional models can be thought of as mixture models, where members of the population are sampled at random. Conversely, mixture models can be thought of as compositional models, where the total size of the population has been normalized to 1.