PV021 Neural networks
Exam manual
This manual specifies knowledge demanded at the PV021 exam. Please, keep
in mind that the knowledge described below is mandatory even for the E grade.
Missing a single part automatically means F. You are supposed to know everything
from the course. However, in some parts you have to know all details of
all formulae, all proofs etc.
Here they are:
• nn lectures 1-4.pdf
– Slides 17 - 54: You need to know all definitions, formally, using the
mathematical notation. You need to be able to explain and demonstrate
the geometric interpretation of a neuron. Keep in mind that I
may demand complete proofs (e.g. slide 43), or at least the basic idea
(slide 45). You do not need to memorize the exact numbers from the
slide 52 but know the claims about computability.
– Slides 76 - 87. Everything in great detail. You need to be able
to provide all mathematical details as well as understanding of the
fundamental notions such as maximum likelihood and all proofs.
• nn lecture 5.pdf: and nn lectures 6-7.pdf
Everything in great detail including all details of all proofs (including the
handwritten ones). You also need to be able to explain what the formulae
mean.
• nn lectures 8-10.pdf
– slides 115 - 162. All details of all observations and methods except:
∗ Slide 126: Just know roughly what the theorem says.
∗ Slide 134: Do not have to memorize all the schedules, just understand
that there is a scheduling and be able to demonstrate
one schedule.
∗ Slide 143: You do not need to memorize 1.7159 but have to know
why the number is this.
∗ Slide 149: You do not have to memorize all the ReLU variants,
just know one.
∗ Slides 150, 151: No need to memorize, fine to know. Let me
stress that apart from the above exceptions, you need to have
a detailed knowledge including the mathematical formulae (e.g.
for the momentum, AdaGrad etc.) and intuitive understanding.
– Slides 203 - 215: Everything in great detail including all the handwritten
stuff. You may be asked to derive the backpropagation algorithm
for CNN even though it did not explicitly appear in the lecture
1
(but is similar to the derivation for MLP). It also helps to know the
intuition for CNN from the applications (slides 176 - 201).
• nn lecture 11.pdf
Be able to explain the visualization methods.
• nn lecture 12.pdf
Slides 217 - 231: All details including all the handwritten stuff. You may
be asked to derive the backpropagation algorithm for RNN even though it
did not explicitly appear in the lecture (but is similar to the derivation for
MLP). You have to know how LSTM is defined (formally and intuitively).
• nn lecture 13.pdf
Everything with all mathematical details presented in the slides and intuition
presented at the lecture (except the slides 266 - 269 that were not
part of the lecture).
2