The ‘Natural Language Processing (NLP): Deep Learning in Python’ course will teach fundamental concepts of NLP (natural language processing). Students will also learn about the GloVe method, matrix factorization, which is a popular algorithm for recommender systems.
The course covers word2vec, GloVe, word embeddings, and sentiment analysis with recursive nets. This course focuses on how to build and understand API via experimentation. The course is usually available for INR 1,999 on Udemy but students can click on the link and get the ‘Natural Language Processing (NLP): Deep Learning in Python’ for INR 449.
Who all can opt for this course?
- Anyone who desire to build word vector representations for various NLP applications, including students and pros
- Modern neural network architectures like recursive neural networks are of interest to professionals and students
- Should not: Anyone who is unsure about the requirements
Course Highlights
| Key Highlights | Details |
|---|---|
| Registration Link | Apply Now! |
| Price | INR 449 ( |
| Duration | 12 Hours |
| Rating | 4.5/5 |
| Student Enrollment | 43,666 students |
| Instructor | Lazy Programmer Inc. https://www.linkedin.com/in/lazyprogrammerinc. |
| Topics Covered | NLP, Neural networks, Word embeddings, Word2Vec, GloVe |
| Course Level | Intermediate |
| Total Student Reviews | 7,369 |
Learning Outcomes
- Comprehend and use word2vec
- Understanding word2vec’s CBOW approach
- Recognize word2vec’s skip-gram technique
- Recognize word2vec’s negative sampling optimisation
- Recognize and apply GloVe using alternating least squares and gradient descent
- Recurrent neural networks can be used to tag words in voice
- Recurrent neural networks can be used to recognise named entities
- Recognize and use recursive neural networks to analyse sentiment
- For sentiment analysis, comprehend and use recursive neural tensor networks
- Gensim can be used to get pretrained word vectors and calculate analogies and similarities
Course Content
| S.No. | Module (Duration) | Topics |
|---|---|---|
| 1. | Outline, Review, and Logistical Things (28 minutes) | Introduction, Outline, and Review |
| How to Succeed in this Course | ||
| Where to get the code / data for this course | ||
| Preprocessed Wikipedia Data | ||
| How to Open Files for Windows Users | ||
| 2. | Beginner’s Corner: Working with Word Vectors (58 minutes) | What are vectors? |
| What is a word analogy? | ||
| Trying to find and assess word vectors using TF-IDF and t-SNE | ||
| Pretrained word vectors from GloVe | ||
| Pretrained word vectors from word2vec | ||
| Text Classification with word vectors | ||
| Text Classification in Code | ||
| Using pretrained vectors later in the course | ||
| Suggestion Box | ||
| 3. | Review of Language Modeling and Neural Networks (01 hour 22 minutes) | Review Section Intro |
| Bigrams and Language Models | ||
| Bigrams in Code | ||
| Neural Bigram Model | ||
| Neural Bigram Model in Code | ||
| Neural Network Bigram Model | ||
| Neural Network Bigram Model in Code | ||
| Improving Efficiency | ||
| Improving Efficiency in Code | ||
| Review Section Summary | ||
| 4. | Word Embeddings and Word2Vec (01 hour 22 minutes) | Return of the Bigram |
| CBOW | ||
| Skip-Gram | ||
| Hierarchical Softmax | ||
| Negative Sampling | ||
| Negative Sampling – Important Details | ||
| Why do I have 2 word embedding matrices and what do I do with them? | ||
| Word2Vec implementation tricks | ||
| Word2Vec implementation outline | ||
| Word2Vec in Code with Numpy | ||
| Tensorflow or Theano – Your Choice! | ||
| Word2Vec Tensorflow Implementation Details | ||
| Word2Vec Tensorflow in Code | ||
| Alternative to Wikipedia Data: Brown Corpus | ||
| 5. | Word Embeddings using GloVe (01 hour 39 minutes) | GloVe Section Introduction |
| Matrix Factorization for Recommender Systems – Basic Concepts | ||
| Matrix Factorization Training | ||
| Expanding the Matrix Factorization Model | ||
| Regularization for Matrix Factorization | ||
| GloVe – Global Vectors for Word Representation | ||
| Recap of ways to train GloVe | ||
| GloVe in Code – Numpy Gradient Descent | ||
| GloVe in Code – Alternating Least Squares | ||
| GloVe in Tensorflow with Gradient Descent | ||
| Visualizing country analogies with t-SNE | ||
| Hyperparameter Challenge | ||
| Training GloVe with SVD (Singular Value Decomposition) | ||
| 6. | Unifying Word2Vec and GloVe (19 minutes) | Pointwise Mutual Information – Word2Vec as Matrix Factorization |
| PMI in Code | ||
| 7. | Using Neural Networks to Solve NLP Problems (01 hour 21 minutes) | Parts-of-Speech (POS) Tagging |
| How can neural networks be used to solve POS tagging? | ||
| Parts-of-Speech Tagging Baseline | ||
| Parts-of-Speech Tagging Recurrent Neural Network in Theano | ||
| Parts-of-Speech Tagging Recurrent Neural Network in Tensorflow | ||
| How does an HMM solve POS tagging? | ||
| Parts-of-Speech Tagging Hidden Markov Model (HMM) | ||
| Named Entity Recognition (NER) | ||
| Comparing NER and POS tagging | ||
| Named Entity Recognition Baseline | ||
| Named Entity Recognition RNN in Theano | ||
| Named Entity Recognition RNN in Tensorflow | ||
| Hyperparameter Challenge II | ||
| 8. | Recursive Neural Networks (Tree Neural Networks) (01 hour 10 minutes) | Recursive Neural Networks Section Introduction |
| Sentences as Trees | ||
| Data Description for Recursive Neural Networks | ||
| What are Recursive Neural Networks / Tree Neural Networks (TNNs)? | ||
| Building a TNN with Recursion | ||
| Trees to Sequences | ||
| Recursive Neural Tensor Networks | ||
| RNTN in Tensorflow (Tips) | ||
| RNTN in Tensorflow (Code) | ||
| Recursive Neural Network in TensorFlow with Recursion | ||
| 9. | Theano and Tensorflow Basics Review (34 minutes) | (Review) Theano Basics |
| (Review) Theano Neural Network in Code | ||
| (Review) Tensorflow Basics | ||
| (Review) Tensorflow Neural Network in Code | ||
| 10. | Setting Up Your Environment (FAQ by Student Request) (37 minutes) | Anaconda Environment Setup |
| How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow | ||
| 11. | Extra Help With Python Coding for Beginners (FAQ by Student Request) (58 minutes) | How to install wp2txt or WikiExtractor.py |
| 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 | ||
| Is Theano Dead? | ||
| 12. | 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) | ||
| 13. | Appendix / FAQ Finale (08 minutes) | What is the Appendix? |
| BONUS |
Resources Required
- Install Sci-Kit Learn, Matplotlib, Numpy, Matplotlib, Theano, and TensorFlow (should be extremely easy by now)
- Being able to independently derive and code the equations requires an understanding of backpropagation and gradient descent
- Create a recurrent neural network using Theano (or Tensorflowfundamental )’s primitives, especially the scan function
- Write a Theano feedforward neural network (or Tensorflow)
- It is advantageous to have knowledge of tree algorithms
Featured Review
Donovan Gonzales (5/5) : This course is good for intermediate deep learning students who are already familiar with a bit of deep learning. The instructor is the best with going into the details and explaining everything piece by piece. Some basics like gradient descent and calculus are required but it’s not too difficult.
Pros
- Henry Chung (5/5) : Awesome tutorial on word embedding (word2vec and glove) techniques with implementations all from scratch.
- Ayush Agarwal (5/5) : You will get the best of both worlds regarding theory and practice.
- Jian Zhang (5/5) : The instructor is very experienced with teaching state of the art machine learning in a pedagogical way.
- Perikumar Javia (5/5) : The developer of the course has perfect directions and pre- requisites in order.
Cons
- Pawe? Luniak (2/5) : Additionaly there are lot of math symbols introduced without explicitly stated what they mean and one have to spend time figuring out what these are.
- Mariana Maroto (2/5) : They make it really hard for windows users to get data.
- Felix Mertineit (1/5) : Mister “Lazy Programmer” does not provide insightful answers to questions asked in the forum.
- Paolo Cabaleiro (2/5) : Examples: – Deep Learning A-Z™: Hands-On Artificial Neural Networks (23 hours) – Python for Data Science and Machine Learning Bootcamp (21.5 hours) Well, I already spent my money here, just don’t like his style.
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, he/she offers 33 Courses and has taught 527,051 Students so far.
- Although Instructor have also been recognised as a data scientist, big data engineer, and full stack software engineer, he currently spend the majority of his time as an artificial intelligence and machine learning engineer with an emphasis on deep learning
- Instructor earned his first master’s degree in computer engineering with a focus on machine learning and pattern recognition more than ten years ago
- Instructor’s 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 advertising and digital media (optimising click and conversion rates) (building data processing pipelines)
- Instructor routinely use big data technologies like Hadoop, Pig, Hive, MapReduce, and Spark
- Instructor developed deep learning models for text modelling, image 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 validated the findings using A/B testing
- Insrtuctor have instructed students at universities like Columbia University, NYU, Hunter College, and The New School in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics
- Instructor’s web programming skills have helped numerous businesses
- Instructor handle all of the server-side backend work, frontend HTML/JS/CSS work, and operations/deployment work
Comparison Table
| Parameters | Natural Language Processing with Deep Learning in Python | Data Science: Natural Language Processing (NLP) in Python | Deep Learning: Convolutional Neural Networks in Python |
|---|---|---|---|
| Offers | INR 455 ( | INR 455 ( | INR 455 ( |
| Duration | 12 hours | 12 hours | 13.5 hours |
| Rating | 4.5 /5 | 4.5 /5 | 4.6 /5 |
| Student Enrollments | 43,664 | 44,286 | 34,673 |
| Instructors | Lazy Programmer Inc. | Lazy Programmer Inc. | Lazy Programmer Inc. |
| Register Here | Apply Now! | Apply Now! | Apply Now! |
Leave feedback about this