Like the course I just released on **Hidden Markov Models**, **Recurrent Neural Networks** are all about learning sequences - but whereas Markov Models are limited by the Markov assumption, Recurrent Neural Networks are not - and as a result, they are more expressive, and more powerful than anything we’ve seen on tasks that we haven’t made progress on in decades.

So what’s going to be in this course and how will it build on the previous neural network courses and Hidden Markov Models?

In the first section of the course we are going to add the concept of**time** to our neural networks.

I’ll introduce you to the**Simple Recurrent Unit**, also known as the **Elman unit**.

We are going to revisit the XOR problem, but we’re going to extend it so that it becomes the parity problem - you’ll see that regular**feedforward neural networks** will have trouble solving this problem but recurrent networks will work because the key is to treat the input as a sequence.

In the next section of the course, we are going to revisit one of the most popular applications of recurrent neural networks -**language modeling**.

You saw when we studied Markov Models that we could do things like generate poetry and it didn’t look too bad. We could even discriminate between 2 different poets just from the sequence of parts-of-speech tags they used.

In this course, we are going to extend our language model so that it no longer makes the Markov assumption.

Another popular application of neural networks for language is**word vectors** or **word embeddings**. The most common technique for this is called **Word2Vec**, but I’ll show you how recurrent neural networks can also be used for creating word vectors.

In the section after, we’ll look at the very popular**LSTM**, or **long short-term memory** unit, and the more modern and efficient **GRU**, or **gated recurrent unit**, which has been proven to yield comparable performance.

We’ll apply these to some more practical problems, such as learning a language model from**Wikipedia data** and visualizing the word embeddings we get as a result.

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!

Suggested Prerequisites:

Tips for success:

So what’s going to be in this course and how will it build on the previous neural network courses and Hidden Markov Models?

In the first section of the course we are going to add the concept of

I’ll introduce you to the

We are going to revisit the XOR problem, but we’re going to extend it so that it becomes the parity problem - you’ll see that regular

In the next section of the course, we are going to revisit one of the most popular applications of recurrent neural networks -

You saw when we studied Markov Models that we could do things like generate poetry and it didn’t look too bad. We could even discriminate between 2 different poets just from the sequence of parts-of-speech tags they used.

In this course, we are going to extend our language model so that it no longer makes the Markov assumption.

Another popular application of neural networks for language is

In the section after, we’ll look at the very popular

We’ll apply these to some more practical problems, such as learning a language model from

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

See you in class!

Suggested Prerequisites:

- calculus
- linear algebra
- 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
- the XOR problem
- Can write a feedforward neural network in Theano and TensorFlow

Tips for success:

- Watch it at 2x.
- Take handwritten notes. This will drastically increase your ability to retain the information.
- Write down the equations. If you don't, I guarantee it will just look like gibberish.
- Ask lots of questions on the discussion board. The more the better!
- Realize that most exercises will take you days or weeks to complete.
- Write code yourself, don't just sit there and look at my code.

- Introduction and Outline (03:18) (FREE preview available)
- Where to get the code (08:26)
- How to Succeed in this Course (05:18)

- Intro to Google Colab, how to use a GPU or TPU for free (12:32)
- Uploading your own data to Google Colab (11:41)
- Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn? (08:54)

- Review Section Introduction (02:37)
- What is Machine Learning? (14:26)
- Code Preparation (Classification Theory) (15:59)
- Beginner's Code Preamble (04:39)
- Classification Notebook (08:40)
- Code Preparation (Regression Theory) (07:18)
- Regression Notebook (10:34)
- The Neuron (09:58)
- How does a model 'learn'? (10:53)
- Making Predictions (06:45)
- Saving and Loading a Model (04:27)
- Suggestion Box (03:04)

- Artificial Neural Networks Section Introduction (06:00)
- Forward Propagation (09:40)
- The Geometrical Picture (09:43)
- Activation Functions (17:18)
- Multiclass Classification (08:41)
- How to Represent Images (12:36)
- Code Preparation (ANN) (12:42)
- ANN for Image Classification (08:36)
- ANN for Regression (11:05)

- Sequence Data (18:27)
- Forecasting (10:35)
- Autoregressive Linear Model for Time Series Prediction (12:01)
- Proof that the Linear Model Works (04:12)
- Recurrent Neural Networks (21:34)
- RNN Code Preparation (05:50)
- RNN for Time Series Prediction (11:11)
- Paying Attention to Shapes (08:27)
- GRU and LSTM (pt 1) (16:09)
- GRU and LSTM (pt 2) (11:36)
- A More Challenging Sequence (09:19)
- Demo of the Long Distance Problem (19:26)
- RNN for Image Classification (Theory) (19:26)
- RNN for Image Classification (Code) (04:00)
- Stock Return Predictions using LSTMs (pt 1) (12:03)
- Stock Return Predictions using LSTMs (pt 2) (05:45)
- Stock Return Predictions using LSTMs (pt 3) (11:59)
- Other Ways to Forecast (05:14)

- Embeddings (13:12)
- Code Preparation (NLP) (13:17)
- Text Preprocessing (05:30)
- Text Classification with LSTMs (08:19)

- Mean Squared Error (09:11)
- Binary Cross Entropy (05:58)
- Categorical Cross Entropy (08:06)

- Gradient Descent (07:52)
- Stochastic Gradient Descent (04:36)
- Momentum (06:10)
- Variable and Adaptive Learning Rates (11:45)
- Adam (11:18)

- Outline of this Course (02:55)
- Review of Important Deep Learning Concepts (03:31)
- Where to get the Code and Data (01:49)
- How to Succeed in this Course (03:13)

- Architecture of a Recurrent Unit (04:39)
- Prediction and Relationship to Markov Models (05:14)
- Unfolding a Recurrent Network (01:56)
- Backpropagation Through Time (BPTT) (04:17)
- The Parity Problem - XOR on Steroids (04:32)
- The Parity Problem in Code using a Feedforward ANN (15:05)
- Theano Scan Tutorial (12:40)
- The Parity Problem in Code using a Recurrent Neural Network (15:14)
- On Adding Complexity (01:16)
- Suggestion Box (03:03)

- Word Embeddings and Recurrent Neural Networks (05:01)
- Word Analogies with Word Embeddings (03:14)
- Representing a sequence of words as a sequence of word embeddings (02:25)
- Generating Poetry (04:23)
- Generating Poetry in Code (part 1) (19:23)
- Generating Poetry in Code (part 2) (04:34)
- Classifying Poetry (03:39)
- Classifying Poetry in Code (16:42)

- Rated RNN Unit (03:25)
- RRNN in Code - Revisiting Poetry Generation (08:49)
- Gated Recurrent Unit (GRU) (05:17)
- GRU in Code (06:28)
- Long Short-Term Memory (LSTM) (04:30)
- LSTM in Code (08:14)
- Learning from Wikipedia Data (06:57)
- Alternative to Wikipedia Data: Brown Corpus (06:03)
- Learning from Wikipedia Data in Code (part 1) (17:56)
- Learning from Wikipedia Data in Code (part 2) (08:38)
- Visualizing the Word Embeddings (11:06)

- Batch Training for Simple RNN (10:25)

- Simple RNN in TensorFlow (07:38)

- What is the Appendix? (02:48)
- Windows-Focused Environment Setup 2018 (20:20)
- How to install wp2txt or WikiExtractor.py (02:21)
- How to install Numpy, Scipy, Matplotlib, Pandas, Sci-Kit Learn, IPython, Theano, and TensorFlow (17:22)
- Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced? (22:04)
- How to Code Yourself (part 1) (15:54)
- How to Code Yourself (part 2) (09:23)
- Proof that using Jupyter Notebook is the same as not using it (12:29)
- What order should I take your courses in? (part 1) (11:18)
- What order should I take your courses in? (part 2) (16:07)
- Python 2 vs Python 3 (04:38)
- How to Succeed in this Course (Long Version) (10:24)
- Is Theano Dead? (10:03)
- Where to get discount coupons and FREE deep learning material (05:31)

- Pre-processed Wikipedia data sample
- Colab Notebooks