Ce sont les mots les plus souvent utilisés dans ce livre.
al
algorithm
although
approach
approximate
approximation
between
binary
case
chapter
class
classification
classifier
compute
consider
corresponding
covariance
data
derivatives
different
distribution
ep
eq
equivalent
error
et
example
exponential
figure
first
form
function
further
gaussian
general
given
gives
gp
however
hyperparameters
information
input
kernel
laplace
latent
learning
let
likelihood
line
linear
log
loss
marginal
matrix
may
mean
methods
model
need
noise
note
notice
number
obtain
obtained
panel
parameters
points
posterior
predictions
predictive
prior
probability
problem
process
random
regression
results
samples
sec
section
see
set
shown
shows
space
squared
targets
terms
test
thus
training
two
use
used
values
variables
variance
vector
weight