# 2.3 Machine learning lecture 4 course notes  (Page 3/5)

 Page 3 / 5
$\epsilon \left(h\right)={P}_{\left(x,y\right)\sim \mathcal{D}}\left(h\left(x\right)\ne y\right).$

I.e. this is the probability that, if we now draw a new example $\left(x,y\right)$ from the distribution $\mathcal{D}$ , $h$ will misclassify it.

Note that we have assumed that the training data was drawn from the same distribution $\mathcal{D}$ with which we're going to evaluate our hypotheses (in the definition of generalization error). This issometimes also referred to as one of the PAC assumptions. PAC stands for “probably approximately correct,” which is a framework and set of assumptionsunder which numerous results on learning theory were proved. Of these, the assumption of training and testing on the same distribution, and the assumptionof the independently drawn training examples, were the most important.

Consider the setting of linear classification, and let ${h}_{\theta }\left(x\right)=1\left\{{\theta }^{T}x\ge 0\right\}$ . What's a reasonable way of fitting the parameters $\theta$ ? One approach is to try to minimize the training error, and pick

$\stackrel{^}{\theta }=arg\underset{\theta }{min}\stackrel{^}{\epsilon }\left({h}_{\theta }\right).$

We call this process empirical risk minimization (ERM), and the resulting hypothesis output by the learning algorithm is $\stackrel{^}{h}={h}_{\stackrel{^}{\theta }}$ . We think of ERM as the most “basic” learning algorithm, and it will be thisalgorithm that we focus on in these notes. (Algorithms such as logistic regression can also be viewed as approximations to empirical risk minimization.)

In our study of learning theory, it will be useful to abstract away from the specific parameterization of hypotheses and from issues suchas whether we're using a linear classifier. We define the hypothesis class $\mathcal{H}$ used by a learning algorithm to be the set of all classifiers considered by it. For linearclassification, $\mathcal{H}=\left\{{h}_{\theta }:{h}_{\theta }\left(x\right)=1\left\{{\theta }^{T}x\ge 0\right\},\theta \in {\mathbb{R}}^{n+1}\right\}$ is thus the set of all classifiers over $\mathcal{X}$ (the domain of the inputs) where the decision boundary is linear.More broadly, if we were studying, say, neural networks, then we could let $\mathcal{H}$ be the set of all classifiers representable by some neural network architecture.

Empirical risk minimization can now be thought of as a minimization over the class of functions $\mathcal{H}$ , in which the learning algorithm picks the hypothesis:

$\stackrel{^}{h}=arg\underset{h\in \mathcal{H}}{min}\stackrel{^}{\epsilon }\left(h\right)$

## The case of finite $\mathcal{H}$

Let's start by considering a learning problem in which we have a finite hypothesis class $\mathcal{H}=\left\{{h}_{1},...,{h}_{k}\right\}$ consisting of $k$ hypotheses. Thus, $\mathcal{H}$ is just a set of $k$ functions mapping from $\mathcal{X}$ to $\left\{0,1\right\}$ , and empirical risk minimization selects $\stackrel{^}{h}$ to be whichever of these $k$ functions has the smallest training error.

We would like to give guarantees on the generalization error of $\stackrel{^}{h}$ . Our strategy for doing so will be in two parts: First, we will show that $\stackrel{^}{\epsilon }\left(h\right)$ is a reliable estimate of $\epsilon \left(h\right)$ for all $h$ . Second, we will show that this implies an upper-bound on the generalization error of $\stackrel{^}{h}$ .

Take any one, fixed, ${h}_{i}\in \mathcal{H}$ . Consider a Bernoulli random variable $Z$ whose distribution is defined as follows. We're going to sample $\left(x,y\right)\sim \mathcal{D}$ . Then, we set $Z=1\left\{{h}_{i}\left(x\right)\ne y\right\}$ . I.e., we're going to draw one example, and let $Z$ indicate whether ${h}_{i}$ misclassifies it. Similarly, we also define ${Z}_{j}=1\left\{{h}_{i}\left({x}^{\left(j\right)}\right)\ne {y}^{\left(j\right)}\right\}$ . Since our training set was drawn iid from $\mathcal{D}$ , $Z$ and the ${Z}_{j}$ 's have the same distribution.

We see that the misclassification probability on a randomly drawn example—that is, $\epsilon \left(h\right)$ —is exactly the expected value of $Z$ (and ${Z}_{j}$ ). Moreover, the training error can be written

#### Questions & Answers

Is there any normative that regulates the use of silver nanoparticles?
what king of growth are you checking .?
Renato
What fields keep nano created devices from performing or assimulating ? Magnetic fields ? Are do they assimilate ?
why we need to study biomolecules, molecular biology in nanotechnology?
?
Kyle
yes I'm doing my masters in nanotechnology, we are being studying all these domains as well..
why?
what school?
Kyle
biomolecules are e building blocks of every organics and inorganic materials.
Joe
anyone know any internet site where one can find nanotechnology papers?
research.net
kanaga
sciencedirect big data base
Ernesto
Introduction about quantum dots in nanotechnology
what does nano mean?
nano basically means 10^(-9). nanometer is a unit to measure length.
Bharti
do you think it's worthwhile in the long term to study the effects and possibilities of nanotechnology on viral treatment?
absolutely yes
Daniel
how to know photocatalytic properties of tio2 nanoparticles...what to do now
it is a goid question and i want to know the answer as well
Maciej
characteristics of micro business
Abigail
for teaching engĺish at school how nano technology help us
Anassong
Do somebody tell me a best nano engineering book for beginners?
there is no specific books for beginners but there is book called principle of nanotechnology
NANO
what is fullerene does it is used to make bukky balls
are you nano engineer ?
s.
fullerene is a bucky ball aka Carbon 60 molecule. It was name by the architect Fuller. He design the geodesic dome. it resembles a soccer ball.
Tarell
what is the actual application of fullerenes nowadays?
Damian
That is a great question Damian. best way to answer that question is to Google it. there are hundreds of applications for buck minister fullerenes, from medical to aerospace. you can also find plenty of research papers that will give you great detail on the potential applications of fullerenes.
Tarell
what is the Synthesis, properties,and applications of carbon nano chemistry
Mostly, they use nano carbon for electronics and for materials to be strengthened.
Virgil
is Bucky paper clear?
CYNTHIA
carbon nanotubes has various application in fuel cells membrane, current research on cancer drug,and in electronics MEMS and NEMS etc
NANO
so some one know about replacing silicon atom with phosphorous in semiconductors device?
Yeah, it is a pain to say the least. You basically have to heat the substarte up to around 1000 degrees celcius then pass phosphene gas over top of it, which is explosive and toxic by the way, under very low pressure.
Harper
Do you know which machine is used to that process?
s.
how to fabricate graphene ink ?
for screen printed electrodes ?
SUYASH
What is lattice structure?
of graphene you mean?
Ebrahim
or in general
Ebrahim
in general
s.
Graphene has a hexagonal structure
tahir
On having this app for quite a bit time, Haven't realised there's a chat room in it.
Cied
what is biological synthesis of nanoparticles
Got questions? Join the online conversation and get instant answers! By By By  By Rhodes By    