Quiz
3
-
Results
X
Attempt
1
of
1
Written
Oct
4,
2023
7:40
PM
-
Oct
4,
2023
7:47
PM
Attempt
Score
3/5-60%
Overall
Grade
(Highest
Attempt)
3/5-60
%
Question
1
1/
1
point
Which
of
the
following
statements
are
true
regarding
logistic
regression?
(Select
all
that
apply.)
v
.
Logistic
regression
is
used
for
binary
classification
problems.
v
~
The
output
of
logistic
regression
is
a
probability
score
between
0
and
1.
~
Inlogistic
regression,
the
linearity
assumption
implies
that
the
decision
boundary
is
always
a
straight
line.
v
Logistic
regression
uses
the
mean
squared
error
as
its
primary
loss
function.
Question
2
0/
1
point
Which
of
the
following
best
describes
underfitting?
It
arises
when
the
regression
model
is
too
complex
with
a
high
number
of
features
leading
to
high
variance.
It
refers
to
a
scenario
where
the
regression
model
fits
the
training
data
perfectly
with
zero
residuals.
-
It
happens
when
the
model
is
too
simplistic,
failing
to
capture
the
underlying
patterns
in
the
data.
%
o
Itoccurs
when
the
model
captures
noise
in
the
training
data
and
performs
poorly
on
new,
unseen
data.
Question
3
1/
1
point
Which
of
the
following
best
describes
the
primary
function
of
the
gradient
descent
optimization
algorithm
in
machine
learning?
~
o
ltincrementally
adjusts
model
parameters
to
minimize
a
cost
function
by
following
the
direction
of
steepest
descent.
It
predicts
future
values
based
on
historical
time-series
data.
It
computes
the
maximum
likelihood
estimate
for
a
given
dataset.
It
is
used
to
classify
data
into
distinct
clusters
based
on
inherent
patterns.
Question
4
0/
1
point
In
the
context
of
regularization
techniques
for
machine
learning
models,
how
do
L1
and
L2
regularization
differ?
%
o
L1
regularization
adds
the
sum
of
the
squared
values
of
coefficients
to
the
loss
function, while
L2
adds
the
absolute
values
of
coefficients.
Neither
L1
nor
L2
regularization
has
any
effect
on
the
magnitude
of
the
model
coefficients.
=
L1
regularization
has the
effect
of
shrinking
some
of
the
model's
coefficients
to
zero,
whereas
L2
tends
to
produce
smaller
coefficients
but
doesn't
force
them
to
zero
Both
L1
and
L2
regularization
will
always
perform
better
than
non-regularized
model.
Question
5
1/
1
point
In
the
context
of
linear
regression
optimized
using
gradient descent,
what
role
does
the
learning
rate
play?
It
determines
the
number
of
features
to
be
used
in
the
regression
model.
It
specifies
the
maximum
number
of
iterations
before
the
gradient
descent
algorithm
terminates.
v
o
It
controls
the
magnitude
of
updates
made
to
the
model's
parameters
during
each
iteration.
It
defines
the
correlation
coefficient
between
the
dependent
and
independent
variables.
