پیشنهاد فرادرس

آموزش اپلیکیشن های شبکه عصبی برای Task های یادگیری ماشینی

دسته بندی ها: شبکه های عصبی مصنوعی ، آموزش های OReilly ، هوش مصنوعی ، یادگیری ماشینی (Machine Learning)

این دوره مقدمه ای است بر یادگیری عمیق یا Deep Learning که روش یادگیری ماشینی را با دموهای تعاملی از معروف ترین کتابخانه یادگیری عمیق، TensorFlow و API سطح بالا آن، Keras در زندگی به ارمغان می آورد. ای دوره به اصول و مبانی یادگیری عمیق مانند شبکه عصبی مصنوعی می پردازد. با استفاده از یادگیری مبانی نوت بوک های Jupyter مبتنی بر پایتون و بدون هیچ دانشی از شبکه عصبی می توانید در پایان دوره مدل های پیشرفته یادگیری عمیق بسازید.

سرفصل ها:

  • مقدمه
  • معرفی TensorFlow
  • معرفی Deep Learning
  • شبکه عصبی و Deep Learning
  • اجرای کد
  • معرفی شبکه عصبی مصنوعی
  • نحوه ی عملکرد Deep Learning
  • واحد های عصبی
  • مجموعه های داده برای Deep Learning
  • شبکه های کانولوشن
  • معماری های ConvNet کلاسیک - LeNet-5
  • معماری های ConvNet کلاسیک - AlexNet و VGGNet
  • TensorBoard و تفسیر خروجی های مدل
  • مقايسه کتابخانه هاي پيشرفته Deep Learning
  • مقدمه ای بر TensorFlow
  • مدل سازی در TensorFlow
  • شبکه های انبوه در TensorFlow
  • شبکه های کانولوشن عمیق در TensorFlow
  • ارتقا شبکه های عمیق
  • بهبود عملکرد و تنظیم پارامترها
  • نحوه ی ساختن پروژه یادگیری عمیق
  • خلاصه
به این نوشته امتیاز دهید 1 2 3 4 5 بدون امتیاز
Deep Learning with TensorFlow: Applications of Deep Neural Networks to Machine Learning Tasks Publisher:Addison-WesleyProfessional Author:Jon Krohn Duration:06:36:39

6+ Hours of Video Instruction Deep Learning with TensorFlow LiveLessons is an introduction to Deep Learning that bring the revolutionary machine-learning approach to life with interactive demos from the most ... - Selection from Deep Learning with TensorFlow: Applications of Deep Neural Networks to Machine Learning Tasks [Video]
Release Date: August 2017
ISBN: 9780134770826
Video Description
6+ Hours of Video InstructionDeep Learning with TensorFlow LiveLessons is an introduction to Deep Learning that bring the revolutionary machine-learning approach to life with interactive demos from the most popular Deep Learning library, TensorFlow, and its high-level API, Keras. Essential theory is whiteboarded to provide an intuitive understanding of Deep Learning’s underlying foundations, i.e., artificial neural networks. Paired with tips for overcoming common pitfalls and hands-on code run-throughs provided in Python-based Jupyter notebooks, this foundational knowledge empowers individuals with no previous understanding of neural networks to build powerful state-of-the-art Deep Learning models.The companion materials for this LiveLesson can be found at https://github.com/the-deep-learners/TensorFlow-LiveLessons/.Skill LevelIntermediateLearn How ToBuild Deep Learning models in TensorFlow and KerasInterpret the results of Deep Learning modelsTroubleshoot and improve Deep Learning modelsUnderstand the language and fundamentals of artificial neural networksBuild your own Deep Learning project
Who Should Take This CourseThis course is perfectly suited to software engineers, data scientists, analysts, and statisticians with an interest in Deep Learning. Code examples are provided in Python, so familiarity with it or another object-oriented programming language would be helpful. Previous experience with statistics or machine learning is not necessary.
Course RequirementsSome experience with any of the following are an asset, but none are essential:Object-oriented programming, specifically PythonSimple shell commands, e.g., in BashMachine learning or statisticsFirst-year college calculusAbout the InstructorJon Krohn is the chief data scientist at untapt, a machine learning startup in New York. He leads a Deep Learning Study Group and, having obtained his doctorate in neuroscience from Oxford University, continues to publish academic papers.About Pearson Video TrainingPearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Prentice Hall, Sams, and Que. Topics include: IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at http://www.informit.com/video.
Introduction
Deep Learning with TensorFlow: Introduction
00:02:27
Lesson 1: Introduction to Deep Learning
Topics
00:00:31
1.1 Neural Networks and Deep Learning
00:15:05
1.2 Running the Code in These LiveLessons
00:08:54
1.3 An Introductory Artificial Neural Network
00:29:47
Lesson 2: How Deep Learning Works
Topics
00:00:40
2.1 The Families of Deep Neural Nets and their Applications
00:05:00
2.2 Essential Theory I—Neural Units
00:23:26
2.3 Essential Theory II—Cost Functions, Gradient Descent, and Backpropagation
00:15:39
2.4 TensorFlow Playground—Visualizing a Deep Net in Action
00:15:31
2.5 Data Sets for Deep Learning
00:06:05
2.6 Applying Deep Net Theory to Code I
00:15:10
Lesson 3: Convolutional Networks
Topics
00:00:48
3.1 Essential Theory III—Mini-Batches, Unstable Gradients, and Avoiding Overfitting
00:28:22
3.2 Applying Deep Net Theory to Code II
00:21:14
3.3 Introduction to Convolutional Neural Networks for Visual Recognition
00:05:57
3.4 Classic ConvNet Architectures—LeNet-5
00:15:43
3.5 Classic ConvNet Architectures—AlexNet and VGGNet
00:23:51
3.6 TensorBoard and the Interpretation of Model Outputs
00:13:39
Lesson 4: Introduction to TensorFlow
Topics
00:00:40
4.1 Comparison of the Leading Deep Learning Libraries
00:04:51
4.2 Introduction to TensorFlow
00:27:55
4.3 Fitting Models in TensorFlow
00:30:10
4.4 Dense Nets in TensorFlow
00:34:14
4.5 Deep Convolutional Nets in TensorFlow
00:28:57
Lesson 5: Improving Deep Networks
Topics
00:00:30
5.1 Improving Performance and Tuning Hyperparameters
00:11:49
5.2 How to Build Your Own Deep Learning Project
00:06:07
5.3 Resources for Self-Study
00:02:22
Summary
Deep Learning with TensorFlow: Summary
00:01:15

پیشنهاد فرادرس

محسن در 1397/01/28 ساعت 14:09

سلام.
عالی بود.