EP20: Yann LeCun - part 15/15
December 15, 2025 • 1h 50m 6s
? (?)
00:00.270
you
think
that
the
field
will
ever
figure
out
continual
or
incremental
learning
Yann LeCun (Chief AI Scientist)
00:05.310
sure
yeah
that's
sort
of
a
technical
problem
well
? (?)
00:09.270
well
i
thought
i
thought
catastrophic
forgetting
right
because
your
weights
that
you
trained
so
much
money
on
get
overwritten
sure
Yann LeCun (Chief AI Scientist)
00:15.750
so
you
train
just
a
little
bit
of
it
i
mean
we
don't
already
do
this
with
SSL
right
we
train
a
foundation
model
like
for
video
or
something
like
vijay
patu
you
know
producers
really
good
representations
of
video
and
then
if
you
want
to
train
the
system
for
a
particular
task
you
Yann LeCun (Chief AI Scientist)
00:29.990
train
a
small
head
on
top
of
it
and
that
head
can
be
you
know
along
continuously
and
even
your
word
model
can
be
trained
continuously
that's
not
an
issue
i
don't
see
this
as
like
a
big
a
huge
challenge
frankly
in
fact
raya
heads
to
LPR
simon
and
i
and
a
few
of
our
colleagues
Yann LeCun (Chief AI Scientist)
00:45.270
back
in
two
thousand
five
two
thousand
six
build
a
learning
based
navigation
system
for
mobile
robots
that
had
this
kind
of
idea
so
it
was
it
was
commercial
net
that
was
doing
semantic
segmentation
from
camera
images
and
on
the
fly
the
top
layers
of
that
network
would
be
adapted
Yann LeCun (Chief AI Scientist)
01:05.280
to
the
current
environment
so
you
do
a
good
job
and
the
labels
came
from
short
wrench
uh
traversability
that
were
indicated
by
stereo
vision
essentially
so
yeah
i
mean
you
can
do
this
it's
particularly
if
you
have
multimodal
yeah
i
don't
see
this
as
a
big
challenge
? (?)
01:29.180
it's
been
a
pleasure
to
have
you
Yann LeCun (Chief AI Scientist)
01:31.350
real
pleasure
to
thank
you
so
much
thank
you
thank
you
Autoscroll