Tensorflow 2.0 | Recurrent Neural Networks, LSTMs, GRUs

Name: Tensorflow 2.0 | Recurrent Neural Networks, LSTMs, GRUs
Rating: 4.1 (487 reviews)

Sequence prediction course that covers topics such as: RNN, LSTM, GRU, NLP, Seq2Seq, Attention, Time series prediction

Created byJad Slim, Amer Sh

Last updated 2/2020

English

English [Auto],

What you'll learn

RNN
LSTM
GRU
NLP
Seq2Seq
Attention
Time series

Course content

3 sections • 16 lectures • 1h 14m total length

Introduction - Please watch1:05
Explore advanced recurrent neural networks, including LSTMs and GRUs, with TensorFlow 2.0, requiring Python and familiarity with TensorFlow or Keras, plus feedforward networks and backpropagation.
Additional FREE Content0:05
Information on the Full Course0:03

Introduction to Recurrent Neural Networks6:19
Explore recurrent neural networks and sequential memory for data where order matters, enabling sentiment analysis, image captioning, and translating text with one-to-many, many-to-one, and many-to-many architectures.
Back propogation through time6:14
Explore how recurrent neural networks maintain internal memory across time steps, unfold in time, and train with back propagation through time using gradient descent and error measures.
Project Overview0:53
Create a noisy sine time-series dataset to train a recurrent neural network, following four steps. Recover the sine pattern from sequences using 1500 training steps and 500 prediction steps.
Preparing our data3:28
Prepare a noisy sine-wave dataset in Google Colab by setting a random seed, generating time steps, adding uniform noise, and visualizing both noisy and noise-free data.
Training our network3:59
Build a sequential recurrent network with a simple rnn layer and dense output. Train with means squared error and an adaptive optimizer, then assess predictions.
Final Source Code12:57

For those having trouble with NumPy0:10
Overview0:48
Learn how NumPy enhances Python for quantitative data analysis and scientific computing, offering high-level mathematical functions to work with numerical datasets in data science.
Arrays vs Lists12:03
Explore why NumPy arrays outperform Python lists for numeric operations, and learn vectorized arithmetic, elementwise powers, and universal functions, then compare array operations to list-based loops.
Multidimensional arrays11:46
Discover how n-dimensional arrays are defined by shape and homogeneous data types, create multi-dimensional arrays with arrange, and inspect their shape, indexing, and dtypes like int64.
One Dimensional Slicing3:33
Learn one dimensional slicing of numpy arrays using start, stop, and step indices; stop is exclusive, mirroring python list slicing with examples from 1 to 9 and 3 to 7.
Reshaping3:34
Learn how to reshape one-dimensional and multi-dimensional arrays in numpy, turning a nine-element array into 3x3 and other shapes while preserving data and ensuring element counts match.
Multidimensional Slicing7:20
Explore multidimensional slicing by indexing 2d and 3d arrays, selecting single cells, slicing ranges, using ellipses, step sizes, and boolean conditionals to filter elements.

Requirements

Python
Numpy
Tensorflow or keras
Feed Forward Neural Networks
Back Propagation

Description

This is a preview to the exciting Recurrent Neural Networks course that will be going live soon. Recurrent Networks are an exciting type of neural network that deal with data that come in the form of a sequence. Sequences are all around us such as sentences, music, videos, and stock market graphs. And dealing with them requires some type of memory element to remember the history of the sequences, this is where Recurrent Neural networks come in.

We will be covering topics such as RNNs, LSTMs, GRUs, NLP, Seq2Seq, attention networks and much much more.

You will also be building projects, such as a Time series Prediction, music generator, language translation, image captioning, spam detection, action recognition and much more.

Building these projects will impress even the most senior machine learning developers; and will prepare you to start tackling your own deep learning projects with real datasets to show off to your colleagues or even potential employers.

Sequential Networks are very exciting to work with and allow for the creation of very intelligent applications. If you’re interested in taking your machine learning skills to the next level, then this course is for you!

Who this course is for:

machine learning developers
Data Scientiests

Tensorflow 2.0 | Recurrent Neural Networks, LSTMs, GRUs

What you'll learn

Explore related topics

Course content

Introduction3 lectures • 1min

Recurrent Neural Networks6 lectures • 34min

NumPy Crash Course (Optional)7 lectures • 39min

Requirements

Description

Who this course is for: