CS
678 - Advanced Machine Learning and Neural Networks

__Assignments
– Winter 2017__

Note: All written assignments (except
homework) are to be done with a word processor and be neat and professional.
You will hand in a hard copy at the beginning of class on the due date. Good writing, grammar, punctuation,
organization, etc. are important and will affect your grade.

**Your Model Readings**

Due: January 24

This
assignment will allow you to give me a ranked list of three possible models for
which you will be doing an in-depth implementation and presentation (see
below). It will also give you an
opportunity to explore the field of machine learning a little more. Do a write-up of 1 single spaced page
each on three papers of your choosing in the area of machine learning
which you will hand in at the beginning of class on the due date. At least two
of the papers should be ones you have not read before the semester (and areas
we will not directly cover this semester) and the papers should each cover a
different area in machine learning.
These papers should focus on machine learning models that are new to you
and interesting to you. The papers
should focus on innovative technical aspects of machine learning and not just
applications of machine learning.
As much as possible, choose papers that are relatively recent. For each model, you should a) briefly
describe the main approach and contribution of the paper and b) give your
opinion on the specific strengths, weaknesses, and contributions of the
approach. Grading will be based on
the perceived effort and insights you have gained. Note that we allow one of the papers to
not be new for you. That allows you
to potentially implement a model that you have been considering for your
research, etc. But, if so, it MUST
be a model that you have not already started developing or using in your
research.

In your
hardcopy give me a priority order on the three papers regarding which you would
most like to present. Include the
full reference for each paper. Also
e-mail me PDF files for each paper with the preferred ranking stated. I will let you know which of the three
models you will implement and present.
I will try to follow your ranking, but may choose another if more
appropriate. By appropriate I will
consider:

á
Is
this a doable and reasonable model for a one semester
project.

á
I
prefer that no model is presented by more than one person,
since the presentations are an important part of our learning experience as a
class. It will be first-come
first-serve if multiple people want to do the same model, so you can hand this
in as early as you like.

á
In
some cases, if you request, you may do your model with a team of no greater
than 2 members. In that case, we
will expect a product that exceeds that being done by one person.

Some
good sources for potential papers include *Proceedings
of the International Conference on Machine Learning*, *Proceedings of Neural Information Processing Systems*, *Machine Learning Journal*, *Journal of Artificial Intelligence Research,*
*Journal of Machine Learning Research*,
*Neural Networks*, *IEEE Transactions on Neural Networks*, *Neural Computation, *among others.

**Model of your choice Project and
Presentation**

Hard
copy due at the beginning of class on the day you give your oral presentation
of the model near the end of the semester.
This project should be started early in the semester and go on
concurrently with the deep learning project below. Your write-up should be formatted like a
conference paper (5 page limit).
You will usually have a small bibliography with more than the initial
paper from the readings assignment above.

1)
Implement
an ML model of your choice. This will be a model not previously implemented for
another class. You may choose one of
the models discussed in the class, or one that you have an interest in. The model will come from the ranked list
of 3 possible models you give me in the initial assignment above. You can give it to me sooner and those
who get it in soonest will have highest priority if there are multiple people
wanting to do the same model. I
will then give you the OK to proceed forward. This will allow me to give you feedback
on your choice, and allow more diversity on the models we consider, so we can
all learn from the presentations.

2)
Test the model on at least 2 different data sets and for a
reasonable spread of the learning algorithm parameters. Analyze and discuss your results.

3)
Do a creative experiment with the model and discuss your
findings.

4)
In addition to your written conference style report, you
will prepare a conference style talk (slide presentation) to be given to the
class (~10-15 minutes) at the end of the semester. The talk should motivate your model,
explain how it works, discuss results on your tasks, and give your overall
analysis including recommendations for potential improvements of the model.

You
will hand in an initial project outline proposal shortly after you have the OK,
and then a progress report half way through the semester.

Project
Outline Proposal: (1 page hardcopy
due in class) Due Jan 31

1.
What
other papers you may include in the bibliography

2.
Brief
description of the implementation you will do

3.
What
data sets will you test it on

4.
What
creative experiment(s) are you considering

5.
Proposed
timeline for completion

This
proposal should give your best guess on these issues. If you find better data sets,
experiments, etc. as you work on your project (which is common) you may switch
to those.

Project
Progress Report: (1 page hardcopy
due in class) Due Feb 23

**Deep Learning Project**

Hard
copy due at the beginning of class on the day we all present (~March 30).

1)
You
will use deep learning (or recurrent nets) to solve a task. You may choose any deep learning model
and you may choose your task. (One
common task considered is MNIST
and you may do that if you want. We have the MNIST data in ARFF format here.) If you are doing deep learning for the Model
of your choice project, then you need to do a very different deep learning
model for this project.

2)
First, try to solve your task on a simpler shallow model
(e.g. MLP with one hidden layer) and report your results as a baseline to
compare with.

3)
You may choose from any of the approaches we discuss in
class or any other deep learning (or recurrent net) approaches you would
like. This includes convolution net
approaches, deep belief nets, stacked auto-encoders, LSTMs, BPTT, latest
supervised approaches, etc. You
CANNOT just use standard BP with multiple hidden layers. Use the produced
features as input to your shallow model as at least one comparison with the
baseline. Try some variations on
your deep network to try to get the best accuracy possible. Give and discuss your results. If using an unsupervised approach, try
to refine the weights of the entire network with Backpropagation after your
initial learning and discuss improvements.
If using stacked autoencoders make sure you include mechanisms to
encourage sparsity (e.g. denoising, weight decay, etc).

4)
Implementation – Models are best understood when you implement
them from scratch, understanding the specifics of the algorithm, rather than using
a black box tool already prepared.
In this class we like to get Òunder the hood.Ó For example, Tensorflow is a great tool for doing deep networks, but can
leave you not understanding the internals of the algorithms if you depend too
much on it. On the other hand it is
nice for implementing the many layers, visualizing results, etc. I want you to implement the basic learning
modules of your algorithm. You may
use a tool, like Tensorflow, to aid in testing,
visualizing, trying different architectures, etc., as long as you implement the
basic functionalities of the model yourself, in order to have an in-depth
understanding.

5)
Analyze and discuss your results in a written paper (4 page
limit).

6)
We will set aside one day to do fast (3-5 minutes each)
presentations of your approaches and results so that we can all learn from each
other.