Deep Learning for Beginners: Core Concepts and PyTorch

Focused View

Seungchan Lee,Nami Kim

9:39:44

10 View

1. Deep learning - the big picture

1. Introduction.mp4

04:07

2.1 lecture1.pdf

2. What is Machine Learning exactly.mp4

05:41

3.1 lecture2.pdf

3. Different types of machine learning supervised, unsupervised, and reinforcement.mp4

11:10

4.1 lecture2 2.pdf

4. The big picture.mp4

04:33

5.1 lecture2 3.pdf

5. Deep neural network as features and weights.mp4

07:48

6.1 lecture2 4.pdf

6. Loss functions and training vs inference.mp4

08:16

7.1 lecture2 5.pdf

7. Why deep learning is unintuitive and how to get good at it.mp4

06:22

8.1 lecture2 6.pdf

8. How to make neural networks feel intuitive.mp4

05:47

9.1 lecture2 7.pdf

9. Course overview.mp4

06:02

2. Reinventing deep neural network from scratch

1.1 lecture3.pdf

1. Linear regression and MSE loss.mp4

08:10

2.1 lecture4.pdf

2. Numerical analysis - a.k.a. trial-and-error.mp4

07:21

3.1 lecture5.pdf

3. Network view.mp4

12:11

4.1 lecture6.pdf

4. Perceptrons.mp4

06:36

5.1 lecture7.pdf

5. The Deep in deep learning.mp4

08:30

6.1 lecture8.pdf

6. Activation Function.mp4

08:06

7.1 lecture9.pdf

7. Overparameterization and overfitting.mp4

06:59

8.1 lecture10.pdf

8. Linear Algebra detour.mp4

13:57

9.1 lecture11.pdf

9. Vectorization (= parallelization).mp4

09:35

10.1 lecture12.pdf

10. Scalability and emergent properties.mp4

08:31

11.1 lecture13.pdf

11. Recap of the forward pass and brief introduction to backward pass.mp4

04:27

3. How the model learns on its own - Back Propagation algorithm deep-div

1. The back propagation algorithm.mp4

05:41

2.1 lecture15.pdf

2. Calculus detour.mp4

14:47

3.1 lecture15 2.pdf

3. Calculus detour II.mp4

08:15

4.1 lecture16.pdf

4. Gradient descent.mp4

16:58

5.1 lecture17.pdf

5. Calculus detour - partial derivatives and gradient descent.mp4

08:33

6.1 lecture18.pdf

6. Calculus detour - the Chain Rule.mp4

15:18

7.1 lecture18 2.pdf

7. Calculus detour - the Chain Rule II.mp4

14:43

8.1 lecture19.pdf

8. Computational graph I - forward pass.mp4

06:18

9.1 lecture20.pdf

9. Computational graph II - backward pass.mp4

11:48

10.1 lecture20 2.pdf

10. Computational graph III - backward pass II.mp4

12:16

11.1 lecture21.pdf

11. Computational graph IV - backward pass III.mp4

18:47

12.1 lecture22.pdf

12. Forward and backward pass recap and wrap up.mp4

09:20

4. How to make neural networks work in reality

1.1 lecture23.pdf

1. Vanishing gradient problem.mp4

14:59

2.1 lecture24.pdf

2. Vanishing gradient solutions I.mp4

12:13

3.1 lecture24 2.pdf

3. Vanishing gradient solutions II.mp4

06:57

4.1 lecture25.pdf

4. Stochastic and mini-batch gradient descent.mp4

15:28

5.1 lecture26.pdf

5. Other optimizers I.mp4

10:54

6.1 lecture26 2.pdf

6. Other optimizers II.mp4

06:02

7.1 lecture27.pdf

7. Hyperparameter tuning strategies.mp4

10:36

8.1 lecture28.pdf

8. Batch normalization.mp4

11:07

9.1 lecture29.pdf

9. Overfitting I - problem and solution overview.mp4

11:56

10.1 lecture30.pdf

10. Overfitting II - regularization and drop out.mp4

10:15

11. Softmax activation.mp4

09:06

12. Loss functions.mp4

05:37

13. Cross entropy loss.mp4

10:48

5. Coding deep neural networks in PyTorch and PyTorch Lightning

1. Setting up a coding environment using Anaconda and Jupyter Notebook in Vscode.mp4

05:45

2. Train an MNIST model from scratch in plain PyTorch I.mp4

14:16

3. Train an MNIST model from scratch in plain PyTorch II.mp4

13:41

4. Train an MNIST model from scratch in plain PyTorch III.mp4

16:01

5. Train an MNIST model from scratch in plain PyTorch IV.mp4

16:24

6. Train an MNIST model using PyTorchs nn module I.mp4

16:46

7. Train an MNIST model using PyTorchs nn module II.mp4

16:31

8. Train an MNIST model using PyTorch Lightning I.mp4

12:18

9. Train an MNIST model using PyTorch Lightning II.mp4

15:31

10. Next steps.mp4

19:40

Description

Get an Intuitive Understanding of Deep Learning and Artificial Intelligence

What You'll Learn?

Develop an intuitive understanding of Deep Learning
Visual and intuitive understanding of core math concepts behind Deep Learning
Detailed view of how exactly deep neural networks work beneath the hood
Computational graphs (which libraries like PyTorch and Tensorflow are built on)
Build neural networks from scratch using PyTorch and PyTorch Lightening
You’ll be ready to explore the cutting edge of AI and more advanced neural networks like CNNs, RNNs and Transformers
You'll be able to understand what deep learning experts are talking about in articles and interviews
You’ll be able to start experimenting with your own AI projects using PyTorch

Who is this for?

Students who want learn Deep Learning for the first time

Beginners who want to finally understand Deep Learning at an intuitive level

Professionals looking to supercharge their understanding of Deep Learning fundamentals

What You Need to Know?

Basic Python programming knowledge

Highschool math

A strong desire to learn Deep Learning and Artificial Intelligence

More details

Description
Are you interested in Artificial Intelligence (AI), Machine Learning and Artificial Neural Network?
Are you afraid of getting started with Deep Learning because it sounds too technical?
Have you been watching Deep Learning videos, but still donâ€™t feel like you â€œgetâ€ it?
Iâ€™ve been there myself! I donâ€™t have an engineering background. I learned to code on my own. But AI still seemed completely out of reach.
This course was built to save you many months of frustration trying to decipher Deep Learning. After taking this course, youâ€™ll feel ready to tackle more advanced, cutting-edge topics in AI.
In this course:

We assume as little prior knowledge as possible. No engineering or computer science background required (except for basic Python knowledge). You donâ€™t know all the math needed for Deep Learning? Thatâ€™s OK. We'll go through them all together - step by step.
We'll "reinvent" a deep neural network so you'll have an intimate knowledge of the underlying mechanics. This will make you feel more comfortable with Deep Learning and give you an intuitive feel for the subject.
We'll also build a basic neural network from scratch in PyTorch and PyTorch Lightning and train an MNIST model for handwritten digit recognition.
After taking this course:

Youâ€™ll finally feel you have an â€œintuitiveâ€ understanding of Deep Learning and feel confident expanding your knowledge further.
If you go back to the popular courses you had trouble understanding before (like Andrew Ng's courses or Jeremy Howards' Fastai course), youâ€™ll be pleasantly surprised at how much more you can understand.
You'll be able to understand what experts like Geoffrey Hinton are saying in articles or Andrej Karpathy is saying during Tesla Autonomy Day.
You'll be well equipped with both practical and theoretical understanding to start exploring more advanced neural network architectures like Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), transformers, etc. and start your journey towards the cutting edge of AI, Supervised and Unsupervised learning, and more.
You can start experimenting with your own AI projects using PyTorch and Supervised Learning
This course is perfect for you if you are:

Interested in Deep Learning and PyTorch but struggling with the core concepts
Someone from a non-engineering background transitioning into an engineering career
Familiar with the basics but wish explore more advanced knowledge.
Already working with Deep Learning models, but want to supercharge your understanding
A Python Developer, looking to advance your career
This 9.5 hour course will teach you all the basic concepts as well as the application of your knowledge. You get 40 downloadable resources, full lifetime access, 30-Day Money-Back Guarantee and a Certificate of Completion.
So what stops you from taking a deep dive into the amazing world of Deep Learning?
Who this course is for:
Students who want learn Deep Learning for the first time
Beginners who want to finally understand Deep Learning at an intuitive level
Professionals looking to supercharge their understanding of Deep Learning fundamentals

User Reviews

Rating

average 0

Total votes0

Focused display

I'm currently working on two projects. First, DeepIntuitions is my attempt at bringing more talent into the field of AI. I feel not enough courses out there are kind enough to newcomers in this field. DeepIntuitions course focuses heavily on an intuitive understanding of Deep Learning and aims to make the subject a lot more approachable to people just starting out.My other project is Sidetrek - we help data/ML/AI teams build a modern data/ML/AI pipeline 10x easier and faster using open-source tools.

Nami Kim

Instructor's Courses

My current passion is to learn AI/ML and share my knowledge with many people. I co-created a deep learning class with Seungchan, helping him with course content and materials.My other focus is Sidetrek - we help data/ML/AI teams build a modern data/ML/AI pipeline 10x easier and faster using open-source tools.Prior to Sidetrek, I worked as a product manager at Adobe and a management consultant at McKinsey & Company. I believe in multidisciplinary approach in learning and applying AI.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.