EP20: Yann LeCun - part 8/11
December 15, 2025 • 1h 50m 6s
Yann LeCun (Chief AI Scientist)
00:00.200
so
i'm
not
a
real
computer
scientist
? (?)
00:02.000
OK
but
what
what
Yann LeCun (Chief AI Scientist)
00:05.440
we
should
do
is
learn
kind
of
basic
things
in
mathematics
in
modeling
mathematics
that
can
be
connected
with
reality
you
tend
to
learn
this
kind
of
stuff
in
engineering
in
some
schools
that's
linked
with
computer
science
but
sort
of
you
know
electrical
engineering
mechanical
Yann LeCun (Chief AI Scientist)
00:23.470
engineering
et
cetera
engineering
disciplines
you're
all
you're
running
in
the
US
calculus
one
two
three
that
gives
you
a
good
basis
right
computer
science
you
don't
you
know
you
can
get
away
with
just
calculus
one
that's
not
enough
right
you
know
we're
learning
you
know
Yann LeCun (Chief AI Scientist)
00:37.430
probability
theory
and
linear
algebra
you
know
all
the
stuff
that
are
really
kind
of
basic
and
then
if
you
do
network
engineering
things
like
i
don't
know
control
tiers
or
signal
processing
like
all
of
those
methods
optimization
you
know
all
of
those
methods
are
really
useful
Yann LeCun (Chief AI Scientist)
00:53.950
for
things
like
AI
and
then
you
can
you
can
basically
learn
similar
things
in
physics
because
physics
is
all
about
like
what
should
i
represent
about
reality
to
be
able
to
make
predictive
models
right
and
that's
really
what
intelligence
is
about
so
so
i
think
you
can
learn
most
Yann LeCun (Chief AI Scientist)
01:12.960
of
what
you
need
to
learn
also
if
you
go
through
a
physics
Yann LeCun (Chief AI Scientist)
01:17.510
a
curriculum
but
obviously
you
need
to
learn
enough
computer
science
to
kind
of
program
and
use
computers
and
even
though
AI
is
going
to
help
you
be
more
efficient
at
programming
you
still
need
to
know
like
how
how
to
do
this
what
do
you
think
about
vivec
coding
i
mean
it's
cool
Yann LeCun (Chief AI Scientist)
01:38.310
it
makes
is
going
to
cause
a
funny
kind
of
thing
where
a
lot
of
the
code
that
will
be
written
will
be
used
only
once
because
it's
going
to
become
so
cheap
to
write
code
right
you're
going
to
ask
your
kind
of
AI
assistant
like
you
know
produced
this
graph
or
like
you
know
this
Yann LeCun (Chief AI Scientist)
01:57.750
research
blah
blah
blah
he's
going
to
write
a
little
piece
of
code
to
do
this
or
maybe
it's
an
applet
that
you
need
to
play
with
for
you
know
a
little
simulator
and
you
can
use
it
once
and
throw
it
away
because
so
cheap
to
produce
right
so
the
idea
that
we're
not
going
to
need
Yann LeCun (Chief AI Scientist)
02:12.150
programmers
anymore
is
false
we're
going
to
the
cost
of
generating
software
you
know
has
been
going
down
continuously
for
decades
and
it's
that's
just
the
next
step
of
the
cars
going
down
but
it
doesn't
mean
computers
will
be
less
useful
they're
going
to
be
more
useful
OK
one
Yann LeCun (Chief AI Scientist)
02:34.530
more
question
so
what
do
you
think
about
the
connection
between
neuroscience
and
machine
learning
there
are
some
ideas
a
lot
of
time
that
AI
borrows
from
neuroscience
and
the
other
way
right
predictive
coding
for
example
do
you
think
that
it's
useful
to
use
ideas
from
but
Yann LeCun (Chief AI Scientist)
02:55.030
there's
a
lot
of
inspiration
you
can
get
from
neuroscience
from
biology
in
general
but
neuroscience
in
particular
i
certainly
was
very
influenced
by
classic
work
in
neuroscience
like
you
know
hubble
and
riesel
's
work
on
the
architecture
of
the
visual
cortex
is
basically
what
Yann LeCun (Chief AI Scientist)
03:11.190
led
to
convolutional
nets
right
and
you
know
i
wasn't
the
first
one
to
use
those
ideas
in
in
artificial
neural
nets
right
there
were
people
in
the
sixties
trying
to
do
this
there
were
you
know
people
in
the
eighties
building
locally
connected
networks
with
multiple
layers
they
Yann LeCun (Chief AI Scientist)
03:25.470
didn't
have
ways
to
train
them
with
backdrop
you
know
there
was
the
the
cognitron
the
neo
cognitron
from
fukushima
which
had
a
lot
of
the
ingredients
just
not
proper
learning
algorithm
and
there
was
another
kind
of
aspect
of
the
cognitron
which
is
that
it
was
really
meant
to
be
Yann LeCun (Chief AI Scientist)
03:43.350
a
model
of
the
visual
cortex
so
it
tried
to
reproduce
every
quirks
of
? (?)
03:50.080
biology
for
example
the
fact
that
in
the
brain
you
don't
have
positive
and
negative
weights
you
have
positive
and
negative
neurons
so
all
the
neurons
all
the
synapses
coming
out
of
an
inhibitor
neurons
neurons
have
negative
weights
OK
and
all
the
synapses
coming
out
of
non
? (?)
04:10.790
inhibitory
neurons
have
positive
weights
so
fukushima
implemented
this
in
his
model
right
he
implemented
the
fact
that
you
know
what
neurons
spike
so
we
didn't
have
a
spiking
neuron
model
but
Yann LeCun (Chief AI Scientist)
04:25.510
but
you
cannot
have
a
negative
number
of
spikes
and
so
so
his
function
was
basically
rectification
like
a
rail
you
except
it
had
a
saturation
and
then
he
knew
from
you
know
various
works
that
there
was
some
sort
of
normalization
and
he
had
to
use
this
because
otherwise
there
was
Yann LeCun (Chief AI Scientist)
04:44.320
no
back
props
of
the
activation
in
this
network
would
go
haywire
so
we
had
to
do
like
division
normalization
that
turns
out
to
actually
be
correspond
to
some
theoretical
models
of
the
visual
cortex
that
some
of
our
colleagues
at
the
center
for
neuroscience
said
NYU
have
been
Yann LeCun (Chief AI Scientist)
05:00.310
pushing
like
david
heger
and
people
like
that
so
yeah
i
mean
i
think
neuroscience
is
very
a
source
of
inspiration
you
know
more
more
recently
the
sort
of
macro
architecture
of
the
brain
in
terms
of
you
know
perhaps
the
world
model
and
planning
and
things
like
this
like
how
how
Yann LeCun (Chief AI Scientist)
05:20.310
is
that
reproduced
like
why
do
we
have
a
separate
module
in
the
brain
for
for
for
factual
memory
the
hippocampus
right
and
we
see
this
now
in
certain
neural
net
architectures
that
there
is
like
a
separate
memory
module
right
maybe
that's
a
good
idea
i
think
we're
going
to
have
i
Yann LeCun (Chief AI Scientist)
05:41.590
think
what's
going
to
happen
is
that
we're
going
to
come
up
with
sort
of
new
AI
neural
net
architectures
deep
learning
architectures
and
a
posterior
you
will
discover
that
the
characteristic
that
we
implemented
in
them
actually
exist
in
the
brain
and
in
fact
that's
a
lot
of
Yann LeCun (Chief AI Scientist)
05:58.750
what's
happening
now
in
neuroscience
which
is
that
there
is
a
lot
of
feedback
now
from
AI
to
neuroscience
where
the
best
models
of
human
perception
are
basically
conventional
nets
today
yeah
OK
do
you
have
anything
else
that
you
want
to
add
to
say
to
the
audience
whatever
you
Yann LeCun (Chief AI Scientist)
06:20.400
want
i
think
we
covered
a
lot
of
grounds
i
think
you
you
know
you
want
to
be
careful
who
you
listen
to
so
don't
listen
to
AI
scientists
talking
about
economics
OK
so
when
some
AI
person
or
even
a
business
person
tells
you
AI
is
going
to
put
everybody
out
of
work
talk
to
an
Yann LeCun (Chief AI Scientist)
06:44.030
economist
basically
none
of
them
is
saying
anything
anywhere
close
to
this
OK
and
you
know
the
effect
of
technological
revolutions
on
the
labor
market
is
something
that
a
few
people
have
devoted
their
career
on
doing
none
of
them
is
predicting
massive
unemployment
none
of
them
Yann LeCun (Chief AI Scientist)
07:07.650
is
predicting
that
radiologists
are
going
to
be
all
unemployed
you
know
et
cetera
right
also
realize
that
actually
fielding
practical
applications
of
AI
so
that
there
are
sufficiently
reliable
and
everything
is
super
difficult
and
it's
very
expensive
and
in
previous
waves
of
Yann LeCun (Chief AI Scientist)
07:26.400
interest
AI
the
techniques
that
people
have
put
a
big
hope
in
turned
out
to
be
overly
unwieldy
and
expensive
except
for
a
few
applications
so
there
was
a
big
wave
of
interest
in
expert
systems
Autoscroll