Training and Testing DataYouTube↗  IA↗(long shot)
Education  30.1K views 39 likes 1 dislikes   23 Feb 2015
Udacity 651K subscribers United States YouTube↗


Please select the problem
You must specify your email and describe the problem in detail
Describe your problem in detail if it's not obvious

Click to Play Video Click to Play Video
مرحبًا بكم مجددًا!
welcome back well you just got was
ما حصلتم عليه للتو هو نسبة 88.4% من الصحة بالنسبة لمصنِّف بايز المبسط.
eighty eight point four percent correct
>> 88.4.
for naivebayes
هذا رائع يا شباب.
eighty eight point four awesome guys
>> هل يعني ذلك أن
well does that mean that your
السيارة ذاتية القيادة التي ابتكرتموها تعرضت إلى حادث بنسبة 11.6% من عدد المرات؟
self-driving car only crashed eleven
>> نعم ستتعرض إلى حادث من حين لآخر.
point six percent of the time it'll crash occasionally yeah it's not good
هذا ليس معدلاً جيدًا بالقدر الكافي بالنسبة للسيارات.
enough for cars but it's great for this
>> حسنًا. >> ولكنه رائع بالنسبة إلى هذه الدورة التدريبية.
course it is very good it's much better
>> إنه جيد جدًا. وهو أفضل بكثير من التخمين.
than guessing one of the things that you
أحد الأمور التي قمتم بها في هذا المثال،
did in that example maybe you didn't
ربما على غير إدراكٍ منكم، هو
even realize you were doing it was you
إجراء التدريب والاختبار باستخدام مجموعتين مختلفتين من البيانات.
trained and you tested on two different
>> وفي الحقيقة أحد الأمور بالغة الأهمية في مجال التعلم الآلي هو إجراء التدريب
sets of data and that's actually really important in machine learning we always
والاختبار دائمًا على بيانات مختلفة.
train and test on different data if you
>> إذا لم تقوموا بذلك، فما قد يحدث هو التدريب المفرط
don't do that what can happen is that
لبيانات التدريب.
you can over fit to your training data
وستظنون أنكم تعرفون ما يجري أكثر من ما تعرفونه حقيقةً.
you can think that you know better what's going on then then you actually
>> وهذا أمر بالغ الأهمية لأنه في مجال التعلم الآلي، ينبغي التعميم
know that's really important because in
على البيانات الجديدة التي تكون مختلفة نوعًا ما
machine learning you have to kind of generalize to new data that's somewhat
وإلا كنت سأحفظ جميع البيانات فحسب،
different and I wouldn't we'll just memorize all the data test it on the
وأختبرها على نفس البيانات كبيانات تدريب، وهو ما سيعطي دائمًا نتيجة 100%.
same data as training I would always get
لكن لن يكون لدي أية فكرة عن كيفية تعميم البيانات الجديدة.
your hand a percent but have no clue how to generalize to new data that's right
>> هذا صحيح. لذا فإن ما ينبغي عليكم فعله دائمًا،
so what you should always do and what
وما سنفعله دائمًا في هذه الدورة،
we'll always do in this course is you
هو الاحتفاظ بنسبة 10% تقريبًا من البيانات واستخدامها كمجموعة اختبار.
should save maybe ten percent of your data and you use it as your testing set
وهذه المجموعة هي ما ستستخدمونه فعليًا لمعرفة مدى تقدمكم
and that's what you used to actually
من حيث تعلم الأنماط الموجودة في بياناتكم.
tell you how much progress you're making in terms of learning your patterns and
>> لذا فحين تقدمون تقريرًا بالنتيجة لأنفسكم أو لمديركم أو
your data so when you open your report the results to yourself and to your boss
عميلكم، استخدموا النتائج التي تم اختبارها، لأن ذلك
or the client use the test data result
يعطي فهمًا أفضل لطريقة أداء البيانات عند تدريبها.
because it's a much better fair kind of understanding of how they are doing than your trainer
Similar videos:

Introduction Pt. III
Udacity
81.5K views 130 likes 4 dislikes 23 Feb 2015100% match

Bayesian Probabilities On Your Own - Intro to Machine Learning
Udacity
43.6K views 2 likes 0 dislikes 23 Feb 2015100% match

Information Gain Calculation Part 5 - Intro to Machine Learning
Udacity
28.2K views 9 likes 3 dislikes 23 Feb 2015100% match

Confusion Matrices - Intro to Machine Learning
Udacity
28.3K views 27 likes 51 dislikes 23 Feb 2015100% match

Scatterplots to Predictions - Intro to Machine Learning
Udacity
82K views 22 likes 1 dislikes 23 Feb 2015100% match

Normalizing 3 - Intro to Machine Learning
Udacity
44.6K views 2 likes 8 dislikes 23 Feb 2015100% match

Welcome to SVM
Udacity
18.6K views 14 likes 1 dislikes 23 Feb 2015100% match

Normalizing 1 Solution - Intro to Machine Learning
Udacity
20K views 4 likes 1 dislikes 23 Feb 2015100% match

Classification By Eye Solution - Intro to Machine Learning
Udacity
55.7K views 28 likes 0 dislikes 23 Feb 2015100% match

Playing Around with Kernel Choices - Intro to Machine Learning
Udacity
47.2K views 17 likes 0 dislikes 23 Feb 2015100% match

Posterior Probabilities - Intro to Machine Learning
Udacity
49.1K views 6 likes 0 dislikes 23 Feb 2015100% match

Separating Line - Intro to Machine Learning
Udacity
32.1K views 19 likes 1 dislikes 23 Feb 2015100% match

Bag of Words - Intro to Machine Learning
Udacity
50.5K views 88 likes 63 dislikes 23 Feb 2015100% match

Speed Scatterplot 3 - Intro to Machine Learning
Udacity
81.8K views 12 likes 3 dislikes 23 Feb 2015100% match

Kernel and Gamma - Intro to Machine Learning
Udacity
39.6K views 28 likes 5 dislikes 23 Feb 2015100% match

Weighting by Term Frequency - Intro to Machine Learning
Udacity
20.5K views 38 likes 22 dislikes 23 Feb 2015100% match

Information Gain Calculation Part 2 - Intro to Machine Learning
Udacity
26.5K views 3 likes 5 dislikes 23 Feb 2015100% match

Gaussian Deployment Solution - Intro to Machine Learning
Udacity
31.9K views 8 likes 2 dislikes 23 Feb 2015100% match

Scatterplots to Predictions 2 - Intro to Machine Learning
Udacity
102K views 11 likes 0 dislikes 23 Feb 2015100% match

Intro To Stanley Terrain Classification
Udacity
48.9K views 42 likes 0 dislikes 23 Feb 2015100% match

Constructing a Decision Tree 2nd Split - Intro to Machine Learning
Udacity
26.5K views 6 likes 0 dislikes 23 Feb 2015100% match

Entropy Calculation Part 4 - Intro to Machine Learning
Udacity
28.8K views 2 likes 9 dislikes 23 Feb 2015100% match

Practice Making a New Feature - Intro to Machine Learning
Udacity
34.9K views 6 likes 0 dislikes 23 Feb 2015100% match

Prerequisites
Udacity
80.5K views 158 likes 10 dislikes 23 Feb 201567% match

Introduction Part II
Udacity
90.9K views 164 likes 12 dislikes 23 Feb 201562% match

Kernel Trick
Udacity
64.7K views 161 likes 102 dislikes 23 Feb 201562% match

Gaussian NB Example
Udacity
50.3K views 80 likes 19 dislikes 23 Feb 201562% match

Nonlinear Data - Intro to Machine Learning
Udacity
37K views 11 likes 5 dislikes 23 Feb 201560% match

Getting Started With sklearn
Udacity
38.4K views 41 likes 2 dislikes 23 Feb 201557% match

NB Decision Boundary in Python
Udacity
38.8K views 17 likes 2 dislikes 23 Feb 201557% match


Settings Privacy About Contact Donate