The ‘Deep Learning with Python and Keras’ course gives a thorough introduction to deep learning. The course begin by reviewing Deep Learning applications and giving a quick rundown of machine learning tools and methods. The course describes what Deep Learning is in a simple yet accurate way.
By the end of the course, you will be able to identify issues that Deep Learning can answer, develop and train a range of Neural Network models, and use cloud computing to expedite training and enhance the performance of your model. The course is usually available for INR 2,699 on Udemy but students can click on the link and get the ‘Deep Learning with Python and Keras’ for INR 449.
Who all can opt for this course?
- Software developers those are interested in learning more about data science and the buzz surrounding deep learning
- Anyone who wish to have a solid basic understanding of deep learning and are experienced with machine learning
Course Highlights
| Key Highlights | Details |
|---|---|
| Registration Link | Apply Now! |
| Price | INR 449 ( |
| Duration | 10 Hours |
| Rating | 4.2/5 |
| Student Enrollment | 23,432 students |
| Instructor | Data Weekends https://www.linkedin.com/in/dataweekends |
| Topics Covered | Machine Learning, Deep Learning, Cloud GPUs, Neural Networks |
| Course Level | Intermediate |
| Total Student Reviews | 3,132 |
Learning Outcomes
- To succinctly and precisely define what deep learning is
- To describe how predictive models can be created using deep learning
- T o determine which applications in the real world can profit from deep learning
- Create deep learning models using Python and Keras then install them
- Using deep learning to handle supervised and unsupervised learning issues using time series, tabular data, text, and pictures
- To train and build fully connected, convolutional, and recurrent neural networks
- To be able to adjust a deep learning model’s parameters while being able to examine its internals without feeling intimidated
- To utilise a GPU to train and run models in the cloud
- To calculate the expense of training huge models
- To reuse previously trained models in order to reduce training costs and time (transfer learning)
Course Content
| S.No. | Module (Duration) | Topics |
|---|---|---|
| 1. | Welcome to the course! (37 minutes) | Welcome to the course! |
| Introduction | ||
| Real world applications of deep learning | ||
| Download and install Anaconda | ||
| Installation Video Guide | ||
| Obtain the code for the course | ||
| Course Folder Walkthrough | ||
| Your first deep learning model | ||
| 2. | Data (01 hour 04 minutes) | Section 2 Intro |
| Tabular data | ||
| Data exploration with Pandas code along | ||
| Visual data Exploration | ||
| Plotting with Matplotlib | ||
| Unstructured Data | ||
| Images and Sound in Jupyter | ||
| Feature Engineering | ||
| Exercise 1 Presentation | ||
| Exercise 1 Solution | ||
| Exercise 2 Presentation | ||
| Exercise 2 Solution | ||
| Exercise 3 Presentation | ||
| Exercise 3 Solution | ||
| Exercise 4 Presentation | ||
| Exercise 4 Solution | ||
| Exercise 5 Presentation | ||
| Exercise 5 Solution | ||
| 3. | Machine Learning (02 hours 04 minutes) | Section 3 Intro |
| Machine Learning Problems | ||
| Supervised Learning | ||
| Linear Regression | ||
| Cost Function | ||
| Cost Function code along | ||
| Finding the best model | ||
| Linear Regression code along | ||
| Evaluating Performance | ||
| Evaluating Performance code along | ||
| Classification | ||
| Classification code along | ||
| Overfitting | ||
| Cross Validation | ||
| Cross Validation code along | ||
| Confusion matrix | ||
| Confusion Matrix code along | ||
| Feature Preprocessing code along | ||
| Exercise 1 Presentation | ||
| Exercise 1 solution | ||
| Exercise 2 Presentation | ||
| Exercise 2 solution | ||
| 4. | Deep Learning Intro (01 hour 16 minutes) | Section 4 Intro |
| Deep Learning successes | ||
| Neural Networks | ||
| Deeper Networks | ||
| Neural Networks code along | ||
| Multiple Outputs | ||
| Multiclass classification code along | ||
| Activation Functions | ||
| Feed forward | ||
| Exercise 1 Presentation | ||
| Exercise 1 Solution | ||
| Exercise 2 Presentation | ||
| Exercise 2 Solution | ||
| Exercise 3 Presentation | ||
| Exercise 3 Solution | ||
| Exercise 4 Presentation | ||
| Exercise 4 Solution | ||
| 5. | Gradient Descent (01 hour 45 minutes) | Section 5 Intro |
| Derivatives and Gradient | ||
| Backpropagation intuition | ||
| Chain Rule | ||
| Derivative Calculation | ||
| Fully Connected Backpropagation | ||
| Matrix Notation | ||
| Numpy Arrays code along | ||
| Learning Rate | ||
| Learning Rate code along | ||
| Gradient Descent | ||
| Gradient Descent code along | ||
| EWMA | ||
| Optimizers | ||
| Optimizers code along | ||
| Initialization code along | ||
| Inner Layers Visualization code along | ||
| Exercise 1 Presentation | ||
| Exercise 1 Solution | ||
| Exercise 2 Presentation | ||
| Exercise 2 Solution | ||
| Exercise 3 Presentation | ||
| Exercise 3 Solution | ||
| Exercise 4 Presentation | ||
| Exercise 4 Solution | ||
| Tensorboard | ||
| 6. | Convolutional Neural Networks (01 hour 20 minutes) | Section 6 Intro |
| Features from Pixels | ||
| MNIST Classification | ||
| MNIST Classification code along | ||
| Beyond Pixels | ||
| Images as Tensors | ||
| Tensor Math code along | ||
| Convolution in 1 D | ||
| Convolution in 1 D code along | ||
| Convolution in 2 D | ||
| Image Filters code along | ||
| Convolutional Layers | ||
| Convolutional Layers code along | ||
| Pooling Layers | ||
| Pooling Layers code along | ||
| Convolutional Neural Networks | ||
| Convolutional Neural Networks code along | ||
| Weights in CNNs | ||
| Beyond Images | ||
| Exercise 1 Presentation | ||
| Exercise 1 Solution | ||
| Exercise 2 Presentation | ||
| Exercise 2 Solution | ||
| 7. | Cloud GPUs (01 minutes) | Google Colaboratory GPU notebook setup |
| Floyd GPU notebook setup | ||
| 8. | Recurrent Neural Networks (45 minutes) | Section 8 Intro |
| Time Series | ||
| Sequence problems | ||
| Vanilla RNN | ||
| LSTM and GRU | ||
| Time Series Forecasting code along | ||
| Time Series Forecasting with LSTM code along | ||
| Rolling Windows | ||
| Rolling Windows code along | ||
| Exercise 1 Presentation | ||
| Exercise 1 Solution | ||
| Exercise 2 Presentation | ||
| Exercise 2 Solution | ||
| 9. | Improving performance (01 hour 01 minutes) | Section 9 Intro |
| Learning curves | ||
| Learning curves code along | ||
| Batch Normalization | ||
| Batch Normalization code along | ||
| Dropout | ||
| Dropout and Regularization code along | ||
| Data Augmentation | ||
| Continuous Learning | ||
| Image Generator code along | ||
| Hyperparameter search | ||
| Embeddings | ||
| Embeddings code along | ||
| Movies Reviews Sentiment Analysis code along | ||
| Exercise 1 Presentation | ||
| Exercise 1 Solution | ||
| Exercise 2 Presentation | ||
| Exercise 2 Solution | ||
| Exercise 3 Presentation |
Resources Required
- Experience with control flow (if/else, for loops), Python knowledge, and pythonic constructions (functions, classes, iterables, generators)
- To copy and transfer files, use the bash shell (or a comparable command prompt) and simple commands
- Basic familiarity with linear algebra (what is a vector, what is a matrix, how to calculate dot product)
- Connecting to a cloud machine using SSH
Featured Review
Swapnil Jadhav (5/5) : This is one of the best courses I have ever completed. I knew the concepts but coding and analyzing them was the problem for me. With this course, now I can implement and prototype my ideas better and faster with keras. Looking forward for other relevent courses from “Data Weekends”.
Pros
- Noriyuki Nakae (5/5) : This is the best Deap Learning course in Udemy I have ever taken.
- kim (5/5) : This lecture explains functions being used in ML perfectly, including both codes along and meanings taught in statistics classes.
- Neal Cariello (5/5) : I’m about 15% through and the pace and detail are perfect.
- Gabriela Surpi (5/5) : Wonderful explanation on how to setup a separate environment with all the packages and versions that will be needed and that work well together.
Cons
- Francisco Ramos (2/5) : Unfortunately, the fact that the course is not fully finished and Q&A seems to be abandoned, I feel a bit disappointed and I have no other option but giving it only 2 stars.
- David Aubin (2/5) : I think if he had a qualified reviewer, review the class and fix the missing pieces.
- Eric Peeters (1/5) : Course is not complete (final solution sections are missing), unbalanced (some simple topics get a lot of coverage, complicated topics are rushed).
- Abhijit Bhattacharya (2/5) : I’m comparing this with machine learning A to Z which was extremely well delivered
About the Author
The instructor of this course is Data Weekends who is a Learn the essentials of Data Science in just one weekend. With 4.4 Instructor Rating and 3,174 Reviews on Udemy, he/she offers 3 Courses and has taught 24,661 Students so far.
- Data WeekendsTM are accelerated data science workshops for programmers that teach you how to use predictive analytics on actual data in a short amount of time
- Data analytics, machine learning, deep learning, and reinforcement learning are all topics that are discussed in the course
- They also provide business training and consultancy on data science, machine learning, and deep learning through their parent firm, Catalit LLC
- Francesco Mosconi, PhD, is the founder and principal lecturer of Data Weekends
Comparison Table
| Parameters | Deep Learning with Python and Keras | Artificial Intelligence: Reinforcement Learning in Python | Advanced AI: Deep Reinforcement Learning in Python |
|---|---|---|---|
| Offers | INR 455 ( | INR 455 ( | INR 455 ( |
| Duration | 10 hours | 14.5 hours | 10.5 hours |
| Rating | 4.2/5 | 4.8/5 | 4.6/5 |
| Student Enrollments | 23,414 | 43,648 | 36,737 |
| Instructors | Data Weekends | Lazy Programmer Team | Lazy Programmer Team |
| Register Here | Apply Now! | Apply Now! | Apply Now! |
Leave feedback about this