Modern Deep Learning in Python

  • Category Other
  • Type Tutorials
  • Language English
  • Total size 3.8 GB
  • Uploaded By tutsnode
  • Downloads 253
  • Last checked 1 month ago
  • Date uploaded 4 years ago
  • Seeders 16
  • Leechers 2

Infohash : 1640876D6BD39FC5C464B869655790A9ED46AB55




Description

This course continues where my first course, Deep Learning in Python, left off. You already know how to build an artificial neural network in Python, and you have a plug-and-play script that you can use for TensorFlow. Neural networks are one of the staples of machine learning, and they are always a top contender in Kaggle contests. If you want to improve your skills with neural networks and deep learning, this is the course for you.

You already learned about backpropagation, but there were a lot of unanswered questions. How can you modify it to improve training speed? In this course you will learn about batch and stochastic gradient descent, two commonly used techniques that allow you to train on just a small sample of the data at each iteration, greatly speeding up training time.

You will also learn about momentum, which can be helpful for carrying you through local minima and prevent you from having to be too conservative with your learning rate. You will also learn about adaptive learning rate techniques like AdaGrad, RMSprop, and Adam which can also help speed up your training.

Because you already know about the fundamentals of neural networks, we are going to talk about more modern techniques, like dropout regularization and batch normalization, which we will implement in both TensorFlow and Theano. The course is constantly being updated and more advanced regularization techniques are coming in the near future.

In my last course, I just wanted to give you a little sneak peak at TensorFlow. In this course we are going to start from the basics so you understand exactly what’s going on – what are TensorFlow variables and expressions and how can you use these building blocks to create a neural network? We are also going to look at a library that’s been around much longer and is very popular for deep learning – Theano. With this library we will also examine the basic building blocks – variables, expressions, and functions – so that you can build neural networks in Theano with confidence.

Theano was the predecessor to all modern deep learning libraries today. Today, we have almost TOO MANY options. Keras, PyTorch, CNTK (Microsoft), MXNet (Amazon / Apache), etc. In this course, we cover all of these! Pick and choose the one you love best.

Because one of the main advantages of TensorFlow and Theano is the ability to use the GPU to speed up training, I will show you how to set up a GPU-instance on AWS and compare the speed of CPU vs GPU for training a deep neural network.

With all this extra speed, we are going to look at a real dataset – the famous MNIST dataset (images of handwritten digits) and compare against various benchmarks. This is THE dataset researchers look at first when they want to ask the question, “does this thing work?”

These images are important part of deep learning history and are still used for testing today. Every deep learning expert should know them well.

This course focuses on “how to build and understand“, not just “how to use”. Anyone can learn to use an API in 15 minutes after reading some documentation. It’s not about “remembering facts”, it’s about “seeing for yourself” via experimentation. It will teach you how to visualize what’s happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

“If you can’t implement it, you don’t understand it”

Or as the great physicist Richard Feynman said: “What I cannot create, I do not understand”.
My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratch
Other courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?
After doing the same thing with 10 datasets, you realize you didn’t learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times…

Suggested Prerequisites:

Know about gradient descent
Probability and statistics
Python coding: if/else, loops, lists, dicts, sets
Numpy coding: matrix and vector operations, loading a CSV file
Know how to write a neural network with Numpy

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

Check out the lecture “Machine Learning and AI Prerequisite Roadmap” (available in the FAQ of any of my courses, including the free Numpy course)

Who this course is for:

Students and professionals who want to deepen their machine learning knowledge
Data scientists who want to learn more about deep learning
Data scientists who already know about backpropagation and gradient descent and want to improve it with stochastic batch training, momentum, and adaptive learning rate procedures like RMSprop
Those who do not yet know about backpropagation or softmax should take my earlier course, deep learning in Python, first

Requirements

Be comfortable with Python, Numpy, and Matplotlib
If you do not yet know about gradient descent, backprop, and softmax, take my earlier course, Deep Learning in Python, and then return to this course.

Last Updated 4/2021

Files:

Modern Deep Learning in Python [TutsNode.com] - Modern Deep Learning in Python 18. Setting Up Your Environment (FAQ by Student Request)
  • 1. Windows-Focused Environment Setup 2018.mp4 (308.8 MB)
  • 1. Windows-Focused Environment Setup 2018-en_US.srt (19.0 KB)
  • 2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow-en_US.srt (13.6 KB)
  • 2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow.mp4 (192.0 MB)
9. GPU Speedup, Homework, and Other Misc Topics
  • 2. Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer-en_US.srt (31.1 KB)
  • 2. Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer.mp4 (236.3 MB)
  • 6. Theano vs. TensorFlow-en_US.srt (8.2 KB)
  • 5. How to Improve your Theano and Tensorflow Skills-en_US.srt (5.9 KB)
  • 1. Setting up a GPU Instance on Amazon Web Services-en_US.srt (4.3 KB)
  • 3. Can Big Data be used to Speed Up Backpropagation-en_US.srt (4.1 KB)
  • 4. Exercises and Concepts Still to be Covered-en_US.srt (2.7 KB)
  • 1. Setting up a GPU Instance on Amazon Web Services.mp4 (101.9 MB)
  • 5. How to Improve your Theano and Tensorflow Skills.mp4 (31.9 MB)
  • 6. Theano vs. TensorFlow.mp4 (16.4 MB)
  • 3. Can Big Data be used to Speed Up Backpropagation.mp4 (9.4 MB)
  • 4. Exercises and Concepts Still to be Covered.mp4 (8.7 MB)
20. Effective Learning Strategies for Machine Learning (FAQ by Student Request)
  • 2. Is this for Beginners or Experts Academic or Practical Fast or slow-paced-en_US.srt (30.7 KB)
  • 4. Machine Learning and AI Prerequisite Roadmap (pt 2)-en_US.srt (22.7 KB)
  • 3. Machine Learning and AI Prerequisite Roadmap (pt 1)-en_US.srt (16.0 KB)
  • 1. How to Succeed in this Course (Long Version)-en_US.srt (14.2 KB)
  • 4. Machine Learning and AI Prerequisite Roadmap (pt 2).mp4 (136.4 MB)
  • 3. Machine Learning and AI Prerequisite Roadmap (pt 1).mp4 (134.9 MB)
  • 2. Is this for Beginners or Experts Academic or Practical Fast or slow-paced.mp4 (60.2 MB)
  • 1. How to Succeed in this Course (Long Version).mp4 (24.9 MB)
1. Introduction and Outline
  • 2. External URLs.txt (0.1 KB)
  • 1. Introduction and Outline-en_US.srt (12.0 KB)
  • 3. How to Succeed in this Course-en_US.srt (7.9 KB)
  • 2. Where to get the Code-en_US.srt (7.1 KB)
  • 1. Introduction and Outline.mp4 (51.8 MB)
  • 3. How to Succeed in this Course.mp4 (46.5 MB)
  • 2. Where to get the Code.mp4 (16.6 MB)
19. Extra Help With Python Coding for Beginners (FAQ by Student Request)
  • 1. How to Code by Yourself (part 1)-en_US.srt (21.7 KB)
  • 3. Proof that using Jupyter Notebook is the same as not using it-en_US.srt (13.5 KB)
  • 2. How to Code by Yourself (part 2)-en_US.srt (12.8 KB)
  • 5. Python 2 vs Python 3-en_US.srt (5.8 KB)
  • 4. How to Uncompress a .tar.gz file-en_US.srt (3.8 KB)
  • 3. Proof that using Jupyter Notebook is the same as not using it.mp4 (108.5 MB)
  • 1. How to Code by Yourself (part 1).mp4 (93.6 MB)
  • 2. How to Code by Yourself (part 2).mp4 (29.3 MB)
  • 5. Python 2 vs Python 3.mp4 (10.4 MB)
  • 4. How to Uncompress a .tar.gz file.mp4 (6.4 MB)
3. Stochastic Gradient Descent and Mini-Batch Gradient Descent
  • 1. Stochastic Gradient Descent and Mini-Batch Gradient Descent (Theory)-en_US.srt (20.5 KB)
  • 4. Stochastic Gradient Descent and Mini-Batch Gradient Descent (Code pt 2)-en_US.srt (14.3 KB)
  • 3. Stochastic Gradient Descent and Mini-Batch Gradient Descent (Code pt 1)-en_US.srt (13.3 KB)
  • 2. SGD Exercise Prompt-en_US.srt (4.3 KB)
  • 4. Stochastic Gradient Descent and Mini-Batch Gradient Descent (Code pt 2).mp4 (110.6 MB)
  • 1. Stochastic Gradient Descent and Mini-Batch Gradient Descent (Theory).mp4 (57.6 MB)
  • 3. Stochastic Gradient Descent and Mini-Batch Gradient Descent (Code pt 1).mp4 (52.0 MB)
  • 2. SGD Exercise Prompt.mp4 (9.7 MB)
8. TensorFlow
  • 3. What is a Session (And more)-en_US.srt (17.8 KB)
  • 2. Building a neural network in TensorFlow-en_US.srt (5.7 KB)
  • 1. TensorFlow Basics Variables, Functions, Expressions, Optimization-en_US.srt (5.7 KB)
  • 2. Building a neural network in TensorFlow.mp4 (43.4 MB)
  • 1. TensorFlow Basics Variables, Functions, Expressions, Optimization.mp4 (39.2 MB)
  • 3. What is a Session (And more).mp4 (31.1 MB)
2. Review
  • 1. Review (pt 1) Neuron Predictions-en_US.srt (17.1 KB)
  • 6. Review Code (pt 2)-en_US.srt (14.9 KB)
  • 3. Review (pt 3) Artificial Neural Networks-en_US.srt (14.5 KB)
  • 7. Review Summary-en_US.srt (1.3 KB)
  • 2. Review (pt 2) Neuron Learning-en_US.srt (11.7 KB)
  • 4. Review Exercise Prompt-en_US.srt (7.3 KB)
  • 5. Review Code (pt 1)-en_US.srt (6.9 KB)
  • 6. Review Code (pt 2).mp4 (126.8 MB)
  • 1. Review (pt 1) Neuron Predictions.mp4 (40.5 MB)
  • 3. Review (pt 3) Artificial Neural Networks.mp4 (34.1 MB)
  • 4. Review Exercise Prompt.mp4 (32.2 MB)
  • 5. Review Code (pt 1).mp4 (25.9 MB)
  • 2. Review (pt 2) Neuron Learning.mp4 (22.2 MB)
  • 7. Review Summary.mp4 (4.3 MB)
4. Momentum and adaptive learning rates
  • 6. Adam Optimization (pt 1)-en_US.srt (16.1 KB)
  • 4. Variable and adaptive learning rates-en_US.srt (14.6 KB)
  • 7. Adam Optimization (pt 2)-en_US.srt (13.9 KB)
  • 1. Using Momentum to Speed Up Training-en_US.srt (7.5 KB)
  • 2. Nesterov Momentum-en_US.srt (7.2 KB)
  • 8. Adam in Code-en_US.srt (6.4 KB)
  • 3. Momentum in Code-en_US.srt (6.1 KB)
  • 9. Suggestion Box-en_US.srt (4.5 KB)
  • 5. Constant learning rate vs. RMSProp in Code-en_US.srt (3.9 KB)
  • 6. Adam Optimization (pt 1).mp4 (55.2 MB)
  • 7. Adam Optimization (pt 2).mp4 (52.8 MB)
  • 3. Momentum in Code.mp4 (38.1 MB)
  • 8. Adam in Code.mp4 (30.5 MB)
  • 1. Using Momentum to Speed Up Training.mp4 (25.6 MB)
  • 5. Constant learning rate vs. RMSProp in Code.mp4 (24.2 MB)
  • 4. Variable and adaptive learning rates.mp4 (23.5 MB)
  • 9. Suggestion Box.mp4 (19.4 MB)
  • 2. Nesterov Momentum.mp4 (12.9 MB)
11. Project Facial Expression Recognition
  • 5. Class-Based ANN in Theano-en_US.srt (14.9 KB)
  • 2. Facial Expression Recognition Problem Description-en_US.srt (14.8 KB)
  • 6. Class-Based ANN in TensorFlow-en_US.srt (12.0 KB)
  • 3. The class imbalance problem-en_US.srt (7.4 KB)
  • 1. Facial Expression Recognition Project Introduction-en_US.srt (6.4 KB)
  • 4. Utilities walkthrough-en_US.srt (5.4 KB)
  • 7. Facial Expression Recognition Project Summary-en_US.srt (1.7 KB)
  • 6. Class-Based ANN in TensorFlow.mp4 (97.1 MB)
  • 5. Class-Based ANN in Theano.mp4 (96.2 MB)
  • 2. Facial Expression Recognition Problem Description.mp4 (33.8 MB)
  • 4. Utilities walkthrough.mp4 (26.1 MB)
  • 3. The class imbalance problem.mp4 (15.7 MB)
  • 1. Facial Expression Recognition Project Introduction.mp4 (12.7 MB)
  • 7. Facial Expression Recognition Project Summary.mp4 (3.8 MB)
15. PyTorch
  • 1. PyTorch Basics-en_US.srt (14.2 KB)
  • 2. PyTorch Dropout-en_US.srt (3.0 KB)
  • 3. PyTorch Batch Norm-en_US.srt (2.9 KB)
  • 1. PyTorch Basics.mp4 (83.9 MB)
  • 3. PyTorch Batch Norm.mp4 (36.8 MB)
  • 2. PyTorch Dropout.mp4 (35.8 MB)
12. Modern Regularization Techniques
  • 2. Dropout Regularization-en_US.srt (14.1 KB)
  • 4. Noise Injection-en_US.srt (6.7 KB)
  • 3. Dropout Intuition-en_US.srt (4.4 KB)
  • 1. Modern Regularization Techniques Section Introduction-en_US.srt (2.9 KB)
  • 5. Modern Regularization Techniques Section Summary-en_US.srt (2.6 KB)
  • 2. Dropout Regularization.mp4 (48.8 MB)
  • 4. Noise Injection.mp4 (14.6 MB)
  • 3. Dropout Intuition.mp4 (9.1 MB)
  • 1. Modern Regularization Techniques Section Introduction.mp4 (8.0 MB)
  • 5. Modern Regularization Techniques Section Summary.mp4 (5.3 MB)
13. Batch Normalization
  • 3. Batch Normalization Theory-en_US.srt (13.5 KB)
  • 7. Batch Normalization Theano (part 2)-en_US.srt (7.7 KB)
  • 4. Batch Normalization Tensorflow (part 1)-en_US.srt (6.4 KB)
  • 5. Batch Normalization Tensorflow (part 2)-en_US.srt (6.3 KB)
  • 2. Exponentially-Smoothed Averages-en_US.srt (5.3 KB)
  • 6. Batch Normalization Theano (part 1)-en_US.srt (5.2 KB)
  • 1. Batch Normalization Introduction-en_US.srt (2.4 KB)
  • 8. Noise Perspective-en_US.srt (2.3 KB)
  • 9. Batch Normalization Summary-en_US.srt (2.0 KB)
  • 7. Batch Normalization Theano (part 2).mp4 (76.3 MB)
  • 5. Batch Normalization Tensorflow (part 2).mp4 (66.5 MB)
  • 3. Batch Normalization Theory.mp4 (53.8 MB)
  • 4. Batch Normalization Tensorflow (part 1).mp4 (11.3 MB)
  • 6. Batch Normalization Theano (part 1).mp4 (10.1 MB)
  • 2. Exponentially-Smoothed Averages.mp4 (8.3 MB)
  • 1. Batch Normalization Introduction.mp4 (3.5 MB)
  • 8. Noise Perspective.mp4 (3.3 MB)
  • 9. Batch Normalization Summary.mp4 (3.0 MB)
7. Theano
  • 3. Is Theano Dead-en_US.srt (12.7 KB)
  • 1. Theano Basics Variables, Functions, Expressions, Optimization-en_US.srt (7.0 KB)
  • 2. Building a neural network in Theano-en_US.srt (3.7 KB)
  • 1. Theano Basics Variables, Functions, Expressions, Optimization.mp4 (65.3 MB)
  • 2. Building a neural network in Theano.mp4 (49.9 MB)
  • 3. Is Theano Dead.mp4 (23.1 MB)
6. Weight Initialization
  • 3. Weight Initialization-en_US.srt (10.1 KB)
  • 2. Vanishing and Exploding Gradients-en_US.srt (7.8 KB)
  • 1. Weight Initialization Section Introduction-en_US.srt (1.2 KB)
  • 5. Weight Initialization Section Summary-en_US.srt (2.0 KB)
  • 4. Local vs. Global Minima-en_US.srt (3.4 KB)
  • 3. Weight Initialization.mp4 (15.0 MB)
  • 2. Vanishing and Exploding Gradients.mp4 (13.5 MB)
  • 4. Local vs. Global Minima.mp4 (8.3 MB)
  • 5. Weight Initialization Section Summary.mp4 (3.5 MB)
  • 1. Weight Initialization Section Introduction.mp4 (1.7 MB)
17. Deep Learning Review Topics
  • 1. What's the difference between neural networks and deep learning-en_US.srt (9.8 KB)
  • 2. Manually Choosing Learning Rate and Regularization Penalty-en_US.srt (5.3 KB)
  • 1. What's the difference between neural networks and deep learning.mp4 (27.2 MB)
  • 2. Manually Choosing Learning Rate and Regularization Penalty.mp4 (10.3 MB)
5. Choosing Hyperparameters
  • 3. Grid Search in Code-en_US.srt (8.9 KB)
  • 4. Modifying Grid Search-en_US.srt (1.8 KB)
  • 1. Hyperparameter Optimization Cross-validation, Grid Search, and Random Search-en_US.srt (4.6 KB)
  • 5. Random Search in Code-en_US.srt (4.5 KB)
  • 2. Sampling Logarithmically-en_US.srt (3.8 KB)
  • 3. Grid Search in Code.mp4 (68.5 MB)
  • 5. Random Search in Code.mp4 (39.0 MB)
  • 1. Hyperparameter Optimization Cross-validation, Grid Search, and Random Search.mp4 (7.9 MB)
  • 2. Sampling Logarithmically.mp4 (5.2 MB)
  • 4. Modifying Grid Search.mp4 (2.4 MB)
14. Keras
  • 1. Keras Discussion-en_US.srt (8.8 KB)
  • 2. Keras in Code-en_US.srt (7.2 KB)
  • 3. Keras Functional API-en_US.srt (5.0 KB)
  • 4. How to easily convert Keras into Tensorflow 2.0 code-en_US.srt (1.9 KB)
  • 2. Keras in Code.mp4 (49.2 MB)
  • 3. Keras Functional API.mp4 (29.1 MB)
  • 1. Keras Discussion.mp4 (15.3 MB)
  • 4. How to easily convert Keras into Tensorflow 2.0 code.mp4 (6.2 MB)
21. Appendix FAQ Finale
  • 2. BONUS Where to get discount coupons and FREE deep learning material-en_US.srt (7.5 KB)
  • 1. What is the Appendix-en_US.srt (3.7 KB)
  • 2. BONUS Where to get discount coupons and FREE deep learning material.mp4 (37.8 MB)
  • 1. What is the Appendix.mp4 (8.9 MB)
10. Transition to the 2nd Half of the Course
  • 1. Transition to the 2nd Half of the Course-en_US.srt (6.4 KB)
  • 1. Transition to the 2nd Half of the Course.mp4 (13.0 MB)
16. PyTorch, CNTK, and MXNet
  • 1. PyTorch, CNTK, and MXNet-en_US.srt (1.0 KB)
  • 1. PyTorch, CNTK, and MXNet.mp4 (1.8 MB)
  • TutsNode.com.txt (0.1 KB)
    • .pad
    • 0 (0.0 KB)
    • 1 (134.7 KB)
    • 2 (988.1 KB)
    • 3 (613.9 KB)
    • 4 (99.4 KB)
    • 5 (173.8 KB)
    • 6 (459.6 KB)
    • 7 (551.0 KB)
    • 8 (67.1 KB)
    • 9 (972.7 KB)
    • 10 (828.4 KB)
    • 11 (412.4 KB)
    • 12 (132.5 KB)
    • 13 (739.8 KB)
    • 14 (549.3 KB)
    • 15 (510.5 KB)
    • 16 (677.0 KB)
    • 17 (826.1 KB)
    • 18 (371.1 KB)
    • 19 (855.4 KB)
    • 20 (179.2 KB)
    • 21 (249.8 KB)
    • 22 (26.5 KB)
    • 23 (211.4 KB)
    • 24 (114.7 KB)
    • 25 (834.3 KB)
    • 26 (253.4 KB)
    • 27 (472.7 KB)
    • 28 (577.3 KB)
    • 29 (559.5 KB)
    • 30 (865.6 KB)
    • 31 (984.9 KB)
    • 32 (874.8 KB)
    • 33 (193.3 KB)
    • 34 (216.8 KB)
    • 35 (211.8 KB)
    • 36 (954.2 KB)
    • 37 (188.5 KB)
    • 38 (797.6 KB)
    • 39 (62.8 KB)
    • 40 (912.1 KB)
    • 41 (535.7 KB)
    • 42 (752.3 KB)
    • 43 (886.9 KB)
    • 44 (811.6 KB)
    • 45 (922.1 KB)
    • 46 (104.4 KB)
    • 47 (405.7 KB)
    • 48 (61.5 KB)
    • 49 (800.9 KB)
    • 50 (525.7 KB)
    • 51 (956.8 KB)
    • 52 (832.8 KB)
    • 53 (664.8 KB)
    • 54 (422.4 KB)
    • 55 (629.3 KB)
    • 56 (300.1 KB)
    • 57 (767.1 KB)
    • 58 (979.7 KB)
    • 59 (396.6 KB)
    • 60 (554.7 KB)
    • 61 (996.2 KB)
    • 62 (150.3 KB)
    • 63 (270.5 KB)
    • 64 (669.0 KB)
    • 65 (611.6 KB)
    • 66 (671.3 KB)
    • 67 (883.4 KB)
    • 68 (314.0 KB)
    • 69 (590.5 KB)
    • 70 (969.1 KB)
    • 71 (80.1 KB)
    • 72 (259.9 KB)
    • 73 (683.5 KB)
    • 74 (709.7 KB)
    • 75 (16.4 KB)
    • 76 (79.7 KB)
    • 77 (579.3 KB)
    • 78 (789.8 KB)
    • 79 (726.0 KB)
    • 80 (819.4 KB)
    • 81 (671.4 KB)
    • 82 (247.2 KB)
    • 83 (512.2 KB)
    • 84 (558.5 KB)
    • 85 (752.7 KB)
    • 86 (20.5 KB)
    • 87 (615.8 KB)
    • 88 (207.6 KB)
  • [TGx]Downloaded from torrentgalaxy.to .txt (0.6 KB)

There are currently no comments. Feel free to leave one :)

Code:

  • udp://inferno.demonoid.pw:3391/announce
  • udp://tracker.openbittorrent.com:80/announce
  • udp://tracker.opentrackr.org:1337/announce
  • udp://torrent.gresille.org:80/announce
  • udp://glotorrents.pw:6969/announce
  • udp://tracker.leechers-paradise.org:6969/announce
  • udp://tracker.pirateparty.gr:6969/announce
  • udp://tracker.coppersurfer.tk:6969/announce
  • udp://ipv4.tracker.harry.lu:80/announce
  • udp://9.rarbg.to:2710/announce
  • udp://shadowshq.yi.org:6969/announce
  • udp://tracker.zer0day.to:1337/announce
REVERSE-PROXY 🔄 RP (success) | 1872ms 📄 torrent 🕐 16 Jan 2026, 11:31:19 pm IST ⏰ 10 Feb 2026, 11:31:19 pm IST ✅ Valid for 24d 23h 🔄 Wait 10m