ch.3 to 3,3 + 9 & 9.1

Question 1

Linear Discriminants

Answer 1

خط های جداکننده

Question 2

demonstration

Answer 2

اثبات،

Question 3

dimensional

Answer 3

ابعاد

high dimensional data

Question 4

performance

Answer 4

کارایی

but its performance does not degrade

Question 5

appreciably

Answer 5

خیلی

its performance does not degrade appreciably

Question 6

in the jargon, this means..

Answer 6

به اصطلاح

Question 7

robust

Answer 7

قوی

Question 8

transmitter

fluid

Answer 8

انتقال دهنده.
مایع
transmitter chemicals within the fluid of the brain raise or lower the electrical potential inside the body of the neuron.

Question 9

plasticity

Answer 9

انعطاف،شکل پذیری

The principal concept is plasticity

Question 10

modifying

strength

Answer 10

تغییر\اصلاح

modifying the strength of synaptic connections between neurons, and creating new connections.

Question 11

proportional

correlation

Answer 11

متناسب
ارتباط.
the changes in the strength of synaptic connections are proportional to the correlation in the firing of the two connecting neurons

Question 12

simultaneously

Answer 12

با هم.همزمان
So if two neurons consistently fire simultaneously, then any connection between them will change in strength, becoming stronger.

Question 13

trivial

Answer 13

بدیهی

trivial example

Question 14

conditioning

Answer 14

set prior requirements on (something) before it can occur or be done.

Question 15

salivating

Answer 15

ترشح بزاق

he neurons for salivating over the food and hearing the bell fired simultaneously, and so became strongly connected.

Question 16

assemblies

Answer 16

اجتماع

connections between neurons and assemblies of neurons can be formed when they fire together and can become stronger

Question 17

potentiation

Answer 17

پتانیسیل

Question 18

circumstances

Answer 18

موقعیت

you can see how it reacts in controlled circumstances

Question 19

accurately
entity
extraneous

Answer 19

عینا
وجود
غیراصلی
it extracts only the bare essentials required to accurately represent the entity being studied, removing all of the extraneous details.

Question 20

threshold

Answer 20

استانه

If this sum is greater than the threshold θ then the neuron fires;

Question 21

correspond

Answer 21

مطابق بودن،رابطه داشتن

a set of weighted inputs wi that correspond to the synapses

Question 22

equivalent
membrane
charge

Answer 22

معادل
غشا،پوسته
بار
equivalent to the membrane of the cell that
collects electrical charge)

Question 23

activation

initially

Answer 23

فعال ساز
at first.
an activation function (initially a threshold function) that decides whether the neuron fires (‘spikes’) for the current inputs

Question 24

assumed

Answer 24

فرض

Question 25

real

Answer 25

واقعی
For a real neuron, this is a question of whether the membrane potential is above some threshold.
برای نورون واقعی، این سوال است که آیا پتانسیل غشاء بالاتر از یک آستانه است.

Question 26

summations

Answer 26

جمع

there may be non-linear summations

Question 27

sequence
pulses
encodes

Answer 27

توالی
پالس
رمز گذاری
a sequence of pulses, and it is this spike train that encodes information.

Question 28

sequentially

Answer 28

به ترتیب

Question 29

asynchronous

Answer 29

غیر همزمان

Question 30

dataset
associated
datapoint

Answer 30

مجموعه داده
مرتبط
an identifiable element in a data set.

the dataset that we learn from has the correct output values associated with each datapoint

Question 31

generalisation

Answer 31

تعمیم

Question 32

presumably

Answer 32

احتمالا

Question 33

external

Answer 33

خارجی

Question 34

fasten

Answer 34

بستن
The Perceptron is nothing more than a collection of McCulloch and Pitts neurons together with a set of inputs and some weights to fasten the inputs to the neurons

Question 35

schematic

Answer 35

نموداری , الگو وار
These are not neurons, they are just a nice schematic way of showing how values are fed into the network

این ها نورون نیستند، آنها فقط یک روش اساسی خوب برای نشان دادن اینکه چگونه مقادیر به شبکه منتقل می شوند

Question 36

dimension

Answer 36

بعد,اندازه

Question 37

additive

Answer 37

افزودنی

Question 38

regardless

Answer 38

بدون در نظر گرفتن

Question 39

perceptron

Answer 39

a computer model or computerized machine devised to represent or simulate the ability of the brain to recognize and discriminate.

Question 40

reproduce

Answer 40

دوباره ساختن
since we are doing supervised learning, so we want the Perceptron to learn to reproduce a particular target, that is, a pattern of firing and non-firing neurons for the given input.

Question 41

implementation

Answer 41

پیاده سازی

Question 42

predefine

iterations

Answer 42

پیش تعریف شده
تکرار
but for now we will predefine the maximum number of iterations,
اما در حال حاضر ما حداکثر تعداد تکرارها را از پیش تعریف می کنیم

Question 43

resistant

inaccuracies

Answer 43

مقاوم
عدم دقت
it will be more stable and resistant to noise (errors) and inaccuracies in the data

Question 44

equation

Answer 44

معادله

uses the recall equation,

Question 45

work out

activations

Answer 45

حل کردن
فعال سازی
since it has to work out the activations of the neurons before the error can be calculated and the weights trained.

Question 46

Initialisation

Answer 46

راه اندازی

Question 47

optimisation

optima

Answer 47

بهينه سازي
مقدار مطلوب
finding local optima for general problems

Question 48

derivative

gradient

Answer 48

مشتق
شیب
to compute the derivative of the error function to get the gradient and follow it downhill.

Question 49

discrete

Answer 49

گسسته

discrete problems are not defined on continuous functions,

Question 50

circuit

Answer 50

Lay a circuit onto a computer chip so that none of the tracks cross.

Question 51

initial

Answer 51

اولیه

Question 52

derivatives

Answer 52

مشتقات

Question 53

dimension

Answer 53

بعد

it gives us the gradient in each dimension separately

Question 54

numerical

Answer 54

عددی

numerical inaccuracy

Question 55

discrete

Answer 55

مجزا

Often there will be several discrete parts to a level set,

Question 56

contours

Answer 56

خطوط

Question 57

quadratic

Answer 57

درجه دوم

making a local model of the function as a quadratic form and finding the minimum of that model

Question 58

greedy choices

Answer 58

انتخاب حریص

to make greedy choices and always go downhill as fast as possible at each point

Question 59

iterate

Answer 59

تکرار

iterate the line search until the solution stops changing

Question 60

equations

Answer 60

معادلات

Question 61

subsection

Answer 61

زیر بخش

Question 62

scalar

Answer 62

عددی, نردبانی

Question 63

inverse

Answer 63

معکوس

we actually use the inverse of the Hessian