Dec 3, 2023
Want to learn Machine Learning (ML), Deep Learning (DL), 5G, 6G, and PYTHON?
Check out our schools below!
https://www.iitk.ac.in/mwn/MLDL/index.html
https://www.iitk.ac.in/mwn/IITK6G/index.html
IIT Kanpur Intensive Training School (ITS) on PYTHON for Machine Learning, Neural Networks and Deep Learning
2nd to 22nd December 2023
https://www.iitk.ac.in/mwn/MLDL/index.html
Welcome to the IIT Kanpur Intensive Training School (ITS) on PYTHON for Machine Learning, Neural Networks and Deep Learning. This school, spanning over 3 weeks, is an intensive program for scholars, students, faculty members, industry professionals and R&D staff aspiring to get an in-depth exposure and learn hands-on implementation of the cutting edge algorithms and software for Machine Learning (ML), Neural Networks (NN) and Deep Learning (DL) toward projects, research and placements to further their career. The school will include extensive assisted PYTHON programming sessions, and numerous important packages such as NUMPY, LINALG, MATPLOTLIB, SCIKIT-LEARN, TENSORFLOW, KERAS. The school also includes problem solving sessions to prepare for tests/ job interviews in ML and DL. For an extensive list of lecture modules and hands-on programming projects, please check the PROGRAM
IIT Kanpur PYTHON + MATLAB Training School on 5G/ 6G Wireless Technologies
2nd to 22nd March 2024
https://www.iitk.ac.in/mwn/IITK6G/index.html
Welcome to the PYTHON + MATLAB Training School on 5G/ 6G Wireless Technologies: MIMO, massive MIMO, mmWave MIMO, NOMA, OTFS and IRS. This is a unique cutting edge project based training school that will feature exhaustive lecture modules and several PYTHON/ MATLAB projects/ case-studies on the latest MIMO, Massive MIMO, mmWave MIMO, NOMA technologies for 5G. Also, with 5G systems being rapidly deployed around the globe, there is accelerated development of Beyond 5G (B5G) and 6G wireless technologies that break the barriers of 5G. OTFS is a cutting-edge 2D modulation technique that operates in the Delay-Doppler domain, while Intelligent reflecting surface (IRS) is another novel technology that enables dynamically altering the radio propagation environment to achieve a phenomenal boost in the capacities. Together, these dual technologies are expected to power the shift to 6G. This training school will feature exhaustive tutorial style lecture modules and several intensive supervised PYTHON/ MATLAB/ OCTAVE programming modules so that participants are able to gain practical hands-on experience of working on state-of-the-art 5G/ 6G projects
All modules will be held on evenings and weekends for the convenience of participants. The extensive projects and PYTHON programming for MACHINE LEARNING (ML), NEURAL NETWORKS (NN), DEEP LEARNING (DL), 5G and 6G are of significant value to participants of all backgrounds.
How do these programs benefit YOU?
UG/ PG students: Learn the latest programming techniques in PYTHON and various packages such as NUMPY, LINALG, MATPLOTLIB, PANDAS, SCIKIT-LEARN, SEABORN, TENSORFLOW, KERAS together with practical ML/ NN / DL/ 5G/ 6G knowledge for projects/ thesis and also to gain an unbeatable edge in placements!
PhD Scholars/ Faculty members: Use PYTHON, and various packages such as NUMPY, LINALG, MATPLOTLIB, PANDAS, SCIKIT-LEARN, SEABORN, TENSORFLOW, KERAS for research and also to establish virtual labs or for project guidance in ML/ NN / DL/ 5G/ 6G Technologies with real world datasets!
Industry Professionals: Take your skills to the next level by learning PYTHON, and various packages such as NUMPY, LINALG, MATPLOTLIB, PANDAS, SCIKITLEARN, SEABORN, TENSORFLOW, KERAS, together with principles of Module Design and Analysis using Practical Data Sets for ML/ NN / DL/ 5G/ 6G Technologies!
Learn the latest ML/ NN/ DL/ 5G/ 6G Algorithms, PYTHON Programming & Libraries from experts at IIT Kanpur
PYTHON, Machine Learning, Neural Networks, Deep Learning, 5G and 6G are the top skills for placements in leading global MNCs such as Google, Amazon, facebook, Microsoft, Qualcomm, Broadcom, Samsung, Mediatek and many others!
Our industry participants have come from top global MNCs, Indian R&D Labs below and many more!
Our academic participants have come from IITs, NITs, top national and international educational institutions and more!
Contact Us:
e-mail: [email protected]
Join/ follow us on our social media sites
https://www.facebook.com/people/MWN-Lab-IIT-Kanpur/100063786175713/
https://twitter.com/LabMwn
https://www.linkedin.com/in/mwn-lab-7236231ba/?originalSubdomain=in
[Music]
[Music]
hello welcome to another module in this
massive open online course so we are
looking at various convex optimization
problems such as the least squares and
least norm to round or to round up this
discussion let us look at another
problem which is essentially a
combination of both these problems that
is the least squares and the least norm
problem which is termed as a
regularization okay so we want to look
at an interesting or you can also think
of this as a generalization of the least
squares and the least known of freemar
system that's regular regularization
okay and as I already said what
regularization does is that it combines
the least squares and least norm
combines the LS that is your least
squares plus
the least-known frameworks okay so this
Ellen and what it essentially does just
follows remember we said you we use the
least-squares
framework when we have a linear model or
an overdetermined linear model and
therefore now consider this linear model
a X bar equals y bar this can be over
determined or under determined I will
come to this in a moment so this is a X
bar equal to Y bar this is your linear
model and this vector X bar this is an
unknown vector ok similar to what we had
previously this vector Y bar this is
your observation matrix and the vector
and the matrix a is assumed to be known
okay that is the matrix that is
pertaining to your model or your linear
model okay so this is your observation
vector similar to the channel estimation
problem you can think of this as the
pilot vector that is the output vector
that is a vector of observations are
observed samples of the received samples
at the receiver in the wireless system
okay so now you have your linear model
in addition we also desire so we want to
minimize so we want to minimize the
model error or minimize so it is
desirable to minimize the approximation
error
at the same time we would also like to
minimize plus we would also like to
minimize norm of X bar or basically we
would also like to minimize the energy
that is minimized the energy this can be
thought of in various ways that is
basically to get into an energy
efficient solution or it is known that
vectors which have lower energy have a
higher probability so you are trying to
maximize so considering the prior
probability of such vectors arising in
the problem so you are also trying to
take factor in take into account that
factor all right so this can be thought
of as basically that you can basically
think of this as either maximizing the
efficiency of the solution
or you can also think of this as the
fact that you are trying to maximize the
probability of X bar this is in natural
systems vectors X bar which have lower
energy have a higher probability so you
have typically that's the scenario so
you would like to maximize the
probability of X bar or you can also
think of this is not probability but
rather the likelihood of X bar I think
that's a better word maximize the
likelihood and therefore we would want
to have an trade-off between the
accuracy of the linear model and this
probability / energy efficiency okay so
it would like to so in summary what we
would like to do is you like to it's not
in either or we would like to do both
this rate of accuracy of linear model
for energy efficiency let us say implies
we want to have an objective function
which reflects both correct we want to
have an objective function or an
optimization we want to have an
objective of optimization that achieves
both that achieves both the objectives
and therefore one can formulate the
following optimization problem that is
minimize remember previously to
basically obtain the solution X bar
which best explains why bar or basically
which minimizes the approximation error
you have minimized the norm of X bar
minus y bar whole square that is the
least squares problem this minimizes the
model error now to maximize the in a to
get an energy efficient solution we
would like to minimize the norm of X bar
this minimize norm of X bar square what
we do now is we combine both of these
alright so this basically is the
approximation error
and this is the energy of the solution
and now you are minimizing a linear
combination of this so this is a
weighting factor now lambda here is not
the Lagrange multiplier this is a
weighting factor or it can be a weight
and therefore you have a weighted
objective so you have a weighted
combination of these two objectives one
is approximation error on its energy and
you are minimizing a weighted
combination that is you're taking the
approximation error weighing it by this
energy all right
this process is known as regularization
so you're not just minimizing the
approximation error but you're
regularizing this objective function by
the addition of the energy by the
addition of a component that is
proportional to the energy of the
solution so this process so this
basically encourages solutions that have
lower energy so this constraints this
process is termed as regularization and
this so this process is termed as
and this factor lambda this lambda is
termed as the regularization parameter
this factor lambda is termed as a
regularization parameter and all right
so this is terminus so it basically in a
scenario we would like to achieve both
or attack Cuba trade-off between
accuracy and as well as an energy
efficient solution one can employ this
approach and the process the procedure
to solve this is similar to that similar
to what we've seen before that is I
expand this objective function and it's
rather once you understood the previous
paradigms this one is going to be rather
simple so the solution is found as
follows solution to the optimization
problem above you can also think as this
as the regularize d squares
okay the solution to the regular ice LS
can be found as follows well we have the
objective function f of X bar this is
norm X bar minus y bar whole square plus
lambda times norm X bar whole square
which I can write as know obscure of a
vector is vector transpose times itself
that is for a real vector minus y bar
transpose X bar minus y bar plus lambda
X bar transpose X bar which is equal to
you can write this again as again
similar to what we have seen so many
times before X bar transpose a transpose
minus y bar transpose X bar minus y bar
plus lambda X bar transpose X bar this
is equal to well I can write this as X
bar transpose a transpose a X bar plus
we know that Y transpose Y bar transpose
a X bar and X bar transpose a transpose
Y but these were equal to each other
because these are scalar quantities when
one is the transpose of the other so I
can simply going to write this as minus
2 X bar transpose a transpose Y bar plus
y bar transpose Y bar plus the
regularization factor lambda X bar
transpose X bar and this is your F okay
f of X bar now if you take the gradient
of this with respect to X bar what that
gives us is well twice a transpose is
symmetric so this is twice X bar
transpose px bar the derivative of spice
BX bar so this is twice a transpose X
bar minus twice is what transpose
ceebar derivative is ceebar derivative
the respect or gradient with respect to
where so this will be minus twice a
transpose y bar plus derivative of Y bar
and this does not depend on X so it's
derivative with respect to X bar is zero
plus now this you can write as lambda X
bar transpose identity matrix into X bar
so this will be derivative will be
lambda twice identity matrix into X bar
and now we set this equal to zero to
find the optimum so this implies now the
factors of two will cancel and further
you can write this as e bar a transpose
a plus identity matrix or in fact lambda
times identity matrix into X bar equals
a transpose y bar and this implies that
if you look at this solution this will
be a transpose a or this will be X hat
you can call this as X hat equals a
transpose a plus lambda times I inverse
okay and therefore this is basically the
solution to the you are regular Isley's
quest that I choose a trade-off between
so it solution to your legalized LS
regular is a square and combines both
the criteria combines both your least
squares as you can see the combines the
properties of both the least squares and
the least not okay LS plus Ln least
squares plus lease more it's a solution
of the weighted optimization problem now
a brief note regarding this lambda this
is the regularization parameter now this
needs to be chosen appropriately now
remember the solution is easy but we are
not spoken of or we are not talked about
how to choose this so this lambda which
is the regularization parameter this has
to be chosen appropriate or this lambda
requires tuning what is known as tuning
in sense that one has to fear play
around with this a little bit to get the
best solution alright so you have to
sort of adaptively you might need to
adaptively change this to get the best
to it the obtain the best solution so
this can be chosen either heuristic alee
all this can be adaptively chosen
adapted adapted to changing environment
and typically one needs to have a slight
intuition about the system that is based
on prior experience that is this lambda
can be determined over time based on
observing the system or based on
observing the model for several time
instances and then eventually
determining what is the lambda what is a
value of lambda that best suits or what
is the value of the regularization
parameter that gives the best solution
alright so that is the curing process
okay so this requires basically tuning
or I choose it heuristic aliy or unit
appropriately on it by adapting it to
the changing by adapting it to a
teaching environment and it requires
some intuition into the requires some
intuition or prior knowledge you put it
that way or prior experience
with the operation of the system so as
to determine the lambda that is a
regularization parameter that yields the
best solution
all right so that basically completes
our discussion on that regularized least
squares a little bit combines both the
least squares and least norm flavors of
this people thank you very much
[Music]
[Music]