The ‘Deep Learning Prerequisites: Logistic Regression in Python’ course serves as an introduction to deep learning and neural networks. It covers logistic regression, a well-known and basic method used in machine learning, data science, and statistics.
This course is for you if you want to use your technical or mathematical expertise to make data-driven decisions and optimise your company using scientific principles. The course is usually available for INR 2,799 on Udemy but you can click on the link and get the ‘Deep Learning Prerequisites: Logistic Regression in Python’ for INR 499.
Who all can opt for this course?
- Aspiring big data and data science professionals
- Students who are considering a career in data science or machine learning
- Students who want to learn how things actually work by implementing them in Python because they are sick of boring conventional statistics and prewritten functions in R
- Those who are familiar with machine learning but want to understand how it relates to artificial intelligence
- Individuals with an interest in addressing the computational neuroscience and machine learning divide
Course Highlights
| Key Highlights | Details |
|---|---|
| Registration Link | Apply Now! |
| Price | INR 499 ( |
| Duration | 07 Hours |
| Rating | 4.6/5 |
| Student Enrollment | 28,699 students |
| Instructor | Lazy Programmer Inc. https://www.linkedin.com/in/lazyprogrammerinc. |
| Topics Covered | Python, Machine Learning, Deep Learning, Statistics |
| Course Level | Intermediate |
| Total Student Reviews | 3,993 |
Learning Outcomes
- Python programming from start for logistic regression
- Elucidate the data science applications of logistic regression
- Derive the logistic regression’s error and update algorithm
- Learn how logistic regression functions by using the biological neuron as an example
- Real-world business issues like identifying facial expressions and predicting user behaviours from e-commerce data can be resolved using logistic regression
- Comprehend the purpose of regularisation in machine learning
Course Content
| S.No. | Module (Duration) | Topics |
|---|---|---|
| 1. | Start Here (36 minutes) | Introduction and Outline |
| How to Succeed in this Course | ||
| Statistics vs. Machine Learning | ||
| Review of the classification problem | ||
| Introduction to the E-Commerce Course Project | ||
| Easy first quiz | ||
| 2. | Basics: What is linear classification? What’s the relation to neural networks? (01 hour 02 minutes) | Linear Classification |
| Biological inspiration – the neuron | ||
| How do we calculate the output of a neuron / logistic classifier? – Theory | ||
| How do we calculate the output of a neuron / logistic classifier? – Code | ||
| Interpretation of Logistic Regression Output | ||
| E-Commerce Course Project: Pre-Processing the Data | ||
| E-Commerce Course Project: Making Predictions | ||
| Feedforward Quiz | ||
| Prediction Section Summary | ||
| Suggestion Box | ||
| 3. | Solving for the optimal weights (52 minutes) | Training Section Introduction |
| A closed-form solution to the Bayes classifier | ||
| What do all these symbols mean? X, Y, N, D, L, J, P(Y=1|X), etc. | ||
| The cross-entropy error function – Theory | ||
| The cross-entropy error function – Code | ||
| Visualizing the linear discriminant / Bayes classifier / Gaussian clouds | ||
| Maximizing the likelihood | ||
| Updating the weights using gradient descent – Theory | ||
| Updating the weights using gradient descent – Code | ||
| E-Commerce Course Project: Training the Logistic Model | ||
| Training Section Summary | ||
| 4. | Practical concerns (54 minutes) | Practical Section Introduction |
| Interpreting the Weights | ||
| L2 Regularization – Theory | ||
| L2 Regularization – Code | ||
| L1 Regularization – Theory | ||
| L1 Regularization – Code | ||
| L1 vs L2 Regularization | ||
| The donut problem | ||
| The XOR problem | ||
| Why Divide by Square Root of D? | ||
| Practical Section Summary | ||
| 5. | Checkpoint and applications: How to make sure you know your stuff (08 minutes) | BONUS: Sentiment Analysis |
| BONUS: Exercises + how to get good at this | ||
| 6. | Project: Facial Expression Recognition (40 minutes) | Facial Expression Recognition Project Introduction |
| Facial Expression Recognition Problem Description | ||
| The class imbalance problem | ||
| Utilities walkthrough | ||
| Facial Expression Recognition in Code | ||
| Facial Expression Recognition Project Summary | ||
| 7. | Background Review (04 minutes) | Gradient Descent Tutorial |
| 8. | Setting Up Your Environment (FAQ by Student Request) (37 minutes) | Anaconda Environment Setup |
| How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow | ||
| 9. | Extra Help With Python Coding for Beginners (FAQ by Student Request) (45 minutes) | How to Uncompress a .tar.gz file |
| How to Code by Yourself (part 1) | ||
| How to Code by Yourself (part 2) | ||
| Proof that using Jupyter Notebook is the same as not using it | ||
| Python 2 vs Python 3 | ||
| 10. | Effective Learning Strategies for Machine Learning (FAQ by Student Request) (59 minutes) | How to Succeed in this Course (Long Version) |
| Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced? | ||
| Machine Learning and AI Prerequisite Roadmap (pt 1) | ||
| Machine Learning and AI Prerequisite Roadmap (pt 2) | ||
| 11. | Appendix / FAQ Finale (08 minutes) | What is the Appendix? |
| BONUS |
Resources Required
- Probability, matrix maths, and derivatives
- You ought to be familiar with some fundamental Numpy Stack Python writing
Featured Review
Adriaan Vorster (3/5) : Learning is best reinforced by not trying to get the code examples used in the lectures to work. Refer to the examples that are available on Github.
Pros
- Jeremy J Samuelson (5/5) : Really great! If I could make a request, I’d like to see a section that deals with model performance metrics, like accuracy, precision, recall, and AUROC.
- Nikhil Kini (5/5) : I find these courses the best refreshers on the week of a machine learning job interview.
- Zlatan Kremonic (5/5) : This is the best class I’ve ever taken on logistic regression, and I have a masters in Economics.
- Sanjay Prasad (5/5) : The examples provided are the best, to start the course with.
Cons
- Greg Donald (1/5) : 7) Given all the things I did not like, I will say the instructor appears to know the topic well, just not a good instructor or video producer.
- Abdul Tawab Ajmal Safi (1/5) : I always have a hard time coding along and understanding his material although I am taking it in order.
- Daniel Havir (1/5) : The material is not explained at all, usually just a formula is presented without any comment.
- Greg Donald (1/5) : 1) The instructor speaks in a monotone voice and is not engaging whatsoever.
About the Author
The instructor of this course is Lazy Programmer Inc. who is a Artificial intelligence and machine learning engineer. With 4.6 Instructor Rating and 148,419 Reviews on Udemy, Lazy Programmer offers 33 Courses and has taught 527,254 Students so far.
- Although Lazy Programmer have also been known as a data scientist, big data engineer, and full stack software engineer, he currently devote the majority of his time as an artificial intelligence and machine learning engineer with a focus on deep learning
- He earned his first master’s degree in computer engineering with a focus on machine learning and pattern identification more than ten years ago
- Lazy Programmer second master’s degree in statistics with a focus on financial engineering was awarded to him
- Data scientist and big data engineer with experience in online ads and digital media (optimising click and conversion rates) (building data processing pipelines)
- Lazy Programmer commonly use big data technologies like Hadoop, Pig, Hive, MapReduce, and Spark
- Lazy Programmer has developed deep learning models for text modelling, picture and signal processing, user behaviour prediction, and click-through rate estimation
- In his work with recommendation systems, he used collaborative filtering and reinforcement learning, and they verified the findings using A/B testing
- Lazy Programmer have instructed students at institutions like Columbia University, NYU, Hunter College, and The New School in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics
- His web programming skills have helped numerous companies
- Lazy Programmer handle all of the server-side core work, frontend HTML/JS/CSS work, and operations/deployment work
Comparison Table
| Parameters | Deep Learning Prerequisites: Logistic Regression in Python | Ensemble Machine Learning in Python: Random Forest, AdaBoost | Data Science: Supervised Machine Learning in Python |
|---|---|---|---|
| Offers | INR 499 ( | INR 455 ( | INR 455 ( |
| Duration | 7 hours | 5.5 hours | 6.5 hours |
| Rating | 4.6/5 | 4.8/5 | 4.6/5 |
| Student Enrollments | 28,697 | 15,120 | 20,366 |
| Instructors | Lazy Programmer Inc. | Lazy Programmer Team | Lazy Programmer Team |
| Register Here | Apply Now! | Apply Now! | Apply Now! |
Leave feedback about this