Natural Language Processing with Deep Learning in Python
In this course we are going to look at NLP (natural language processing) with deep learning.
Previously, you learned about some of the basics, like how many NLP problems are just regular machine learning and data science problems in disguise, and simple, practical methods like bag-of-words and term-document matrices.
These allowed us to do some pretty cool things, like detect spam emails, write poetry, spin articles, and group together similar words.
In this course I’m going to show you how to do even more awesome things. We’ll learn not just 1, but 4 new architectures in this course.
First up is word2vec.
In this course, I’m going to show you exactly how word2vec works, from theory to implementation, and you’ll see that it’s merely the application of skills you already know.
Word2vec is interesting because it magically maps words to a vector space where you can find analogies, like:
king - man = queen - woman
France - Paris = England - London
December - Novemeber = July - June
For those beginners who find algorithms tough and just want to use a library, we will demonstrate the use of the Gensim library to obtain pre-trained word vectors, compute similarities and analogies, and apply those word vectors to build text classifiers.
We are also going to look at the GloVe method, which also finds word vectors, but uses a technique called matrix factorization, which is a popular algorithm for recommender systems.
Amazingly, the word vectors produced by GLoVe are just as good as the ones produced by word2vec, and it’s way easier to train.
We will also look at some classical NLP problems, like parts-of-speech tagging and named entity recognition, and use recurrent neural networks to solve them. You’ll see that just about any problem can be solved using neural networks, but you’ll also learn the dangers of having too much complexity.
Lastly, you’ll learn about recursive neural networks, which finally help us solve the problem of negation in sentiment analysis. Recursive neural networks exploit the fact that sentences have a tree structure, and we can finally get away from naively using bag-of-words.
All of the materials required for this course can be downloaded and installed for FREE. We will do most of our work in Numpy, Matplotlib, and Theano. I am always available to answer your questions and help you along your data science journey.
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.
See you in class.
"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:
calculus (taking derivatives)
matrix addition, multiplication
probability (conditional and joint distributions)
Python coding: if/else, loops, lists, dicts, sets
Numpy coding: matrix and vector operations, loading a CSV file
neural networks and backpropagation, be able to derive and code gradient descent algorithms on your own
Can write a feedforward neural network in Theano or TensorFlow
Can write a recurrent neural network / LSTM / GRU in Theano or TensorFlow from basic primitives, especially the scan function
Helpful to have experience with tree algorithms
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)
Get a Reminder
Rating | 3.9★ based on 251 ratings |
---|---|
Length | 12 total hours |
Starts | On Demand (Start anytime) |
Cost | $0 |
From | Udemy |
Instructors | Lazy Programmer Inc., Lazy Programmer Team |
Download Videos | Only via the Udemy mobile app |
Language | English |
Subjects | Data Science Business |
Tags | Data Science Business Development Data & Analytics |
Get a Reminder
Similar Courses
What people are saying
deep learning
This is a serious look at some NLP methods from the deep learning era.
This course has almost everything I need to learn about deep learning with natural language processing.
This course is good for intermediate deep learning students who are already familiar with a bit of deep learning.
I have a good foundation of ML and deep learning and needed NLP knowledge specifically and this course looks pretty good so far It is a very good match for me because now I am being able to understand the mathematics behind all these concepts.
Very Helpful Nice overview over Natural Language Processing and Deep Learning.
The instructor knows a lot about deep learning and the course content is well organized It was really good poor explaination contents are not bad, but not so kind the way it's organised.
Specifically, the current course fares pretty well in explaining the relevant Machine/Deep Learning concepts.
A great series on advanced deep learning application.
This is a really interesting topic, and judging by the current research I think its really important to combine deep learning with natural language processing.
The whole course makes a lot of deep learning topics more understandable on a practical level.
I came here for learning how to apply word vectors, and sentiment analysis with deep learning.
Amazing videos for deep learning enthusiasts.
It comes with good details of mathematics behind the deep learning algorithms.
A good intro to using deep learning for NLP.
Read more
lazy programmer
Mister "Lazy Programmer" does not provide insightful answers to questions asked in the forum.
Very clean and clear Firstly, I have to congratulate the Lazy Programmer because he is the only one on Udemy who tries to unpack systematically the whole Machine/Deep Learning field.
The Lazy Programmer has to add more videos at his tutorials and more comments at his code to show what each part (and even each line!)
Finally, the Lazy Programmer assumes again that everybody knows very well to use Tensorflow and Theano (which is not the case since many of us have used Keras more extensively) and he does not explain almost anything about Tensorflow and Theano.
The first tutorial of the Lazy Programmer about NLP was significantly better in terms of the intelligibility of the code (but it was also dealing with simpler concepts and applications) Notes and references are good.
All the lazy programmer courses are done very well, they give complete preparation but they are very challenging; their sequence forms a pleasant and complete course path; congratulations to the author.
This course is challenging but don't let that deter you since Lazy Programmer answers questions from students in the blink of an eye.
I've learned this topic in a systematic way thanks to the Lazy Programmer.
Definitely not for beginners, but ideal for those who are familiar with deep learning and want to apply it to NLP I highly recommend this course to anyone who wants to learn how NLP works, as well as all previous courses from Lazy Programmer.
My thoughts are valid for your other classes as well Lazy Programmer.
He's teaching really advanced stuff in a very didactic way Claridad en los conceptos Not Descriptive There is no subtitle in videos I realised the courses by Lazy Programmer Inc. are the most useless courses.
Read more
neural networks
Has very good explanations about Word2Vec, GloVe, and recursive neural networks (RNN).
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.
After learning to increase efficiency, word2vec model, and recursive neural networks I am looking forward to learning more.
Very accessible if you have experience in neural networks and deep learning.
The course is not self-contained, it needs many code an explanations from the recurrent neural networks course.
Nice applications of neural networks Lots of good information, but when he's reading lists of results it gets boring and repetitive, and his voice is rather monotone, so I often find myself zoning out.
Read more
for beginners
It's good for beginners and advanced students then since there is something for everyone to enjoy.
It's full of content for beginners and more if you are advanced.
The course is not for beginners but detailed and in-depth as I expected.
Would be challenging for beginners, as the programming exercises are not simple.
Not for beginners, but great for experts.
Read more
word embeddings
The problem selection is interesting and focus on word embeddings and sentiment analysis.
great examples for learning how to build word embeddings.
I would take this course if you want to learn about how word embeddings are made and how they work or if you want to learn to write your own RNTN.
You go through all the details, I have a much clearer intuition for word embeddings now Sim, como todos os cursos que fiz até agora do Lazy Programmer, o curso tem alta qualidade, equilibrando teoria e prática.
Word embeddings and word2vec are explained well and all code is included.
Read more
previous courses
Tried to ask simple questions in Q&A, but got some roundabout responses instead of clear answers or at least links or references to previous courses.
If you are following the complete specialization then it is a good course as the tutor keep referring to previous courses a lot.
Feels like to many copy pastes from author's previous courses.
Good course overall, but too much dependence on other previous courses by the lecturer.
Read more
other courses
It goes really deep where some other courses would try to pack in everything into one course without really teaching anything besides the surface level.
There are other courses which cover all the topics in a single course (or maybe 2), and with great instructors.
What is more, the instructor likes to relate to his other courses, which are supposed to be the prerequisites, but unfortunately its not about the knowledge in these courses (it would be understandable), but rather about some specific vocabulary, symbols and ways of thinking, which one cannot be aware without knowing other courses of this instructor (despite having the prerequisite knowledge).
It has lot of references to other courses.
Read more
Careers
An overview of related careers and their average salaries in the US. Bars indicate income percentile.
Research Scientist-Machine Learning $55k
Cloud Architect - Azure / Machine Learning $75k
Watson Machine Learning Engineer $81k
Machine Learning Software Developer $103k
Software Engineer (Machine Learning) $116k
Applied Scientist, Machine Learning $130k
Autonomy and Machine Learning Solutions Architect $131k
Applied Scientist - Machine Learning -... $136k
RESEARCH SCIENTIST (MACHINE LEARNING) $147k
Machine Learning Engineer 2 $161k
Machine Learning Scientist Manager $170k
Machine Learning Scientist, Personalization $213k
Write a review
Your opinion matters. Tell us what you think.
Please login to leave a review
Rating | 3.9★ based on 251 ratings |
---|---|
Length | 12 total hours |
Starts | On Demand (Start anytime) |
Cost | $0 |
From | Udemy |
Instructors | Lazy Programmer Inc., Lazy Programmer Team |
Download Videos | Only via the Udemy mobile app |
Language | English |
Subjects | Data Science Business |
Tags | Data Science Business Development Data & Analytics |
Similar Courses
Sorted by relevance
Like this course?
Here's what to do next:
- Save this course for later
- Get more details from the course provider
- Enroll in this course