AI for Text, NLP, and Forecasting Training Overview
This live, online Artificial Intelligence (AI) For Text, NLP, and Forecasting training course teaches attendees how to build Recurrent Neural Networks (RNNs) and Long Short-Term Memory networks (LSTMs) to apply sequence models to natural language processing (NLP). Participants learn how to implement these models from the ground up using Keras/TensorFlow by initially building a shallow neural network and then progressing to Deep Learning (DL) architectures.
Location and Pricing
This course is taught as a private, live online class for teams of 3 or more. All our courses are hands-on, instructor-led, and tailored to fit your group’s goals and needs. Most Accelebrate classes can be flexibly scheduled for your group, including delivery in half-day segments across a week or set of weeks. To receive a customized proposal and price quote for online corporate training, please contact us.
In addition, some courses are available as live, instructor-led training from one of our partners.
Objectives
- Compare AI versus ML versus DL
- Work with TensorFlow and Keras
- Use sequence algorithms
- Work with Recurrent Neural Networks (RNN)
- Implement use cases for Recurrent Neural Networks
- Use RNN variants such as Long short-term memory (LSTM)
- Discuss text and language processing applications for AI
- Implement natural language processing (NLP)
Prerequisites
All students must have basic Python experience and an understanding of machine learning.
Outline
Expand All | Collapse All
Introduction
Compare AI vs ML vs DL
Introduction to Neural Networks
- The math behind neural networks
- Activation functions
- Vanishing gradient problem and ReLU
- Loss functions
- Gradient descent
- Back propagation
- Understanding the intuition behind neural networks
Introducing Perceptrons
- Single Layer linear classifier
- Step Function
- Updating the weights
- Linear separability and XOR problem
- Hidden Layers: Intro to Deep Neural Networks and Deep Learning
- Hidden Layers as a solution to XOR problem
- The architecture of deep learning
Introducing Keras/TensorFlow
- What is Keras?
- Using Keras with a TensorFlow Backend
Introducing TensorFlow
- TensorFlow intro
- TensorFlow Features
- TensorFlow Versions
- GPU and TPU scalability
- The Tensor: The Basic Unit of TensorFlow
Introducing Tensors
- TensorFlow Execution Model
- Recurrent Neural Networks in Keras/TensorFlow
Long Short-Term Memory (LSTM) in TensorFlow
Text processing elements
TF-IDF
Word2vec
Tokenizers, N-grams
Stopword Removal
Sentiment Analysis
Text Processing Pipelines
Natural Language Processing
- What is NLP?
- Sensory Acuity
- Behavioral Flexibility
- NLP Techniques
- NLP and Deep Learning
Word2vec
Learning Word Embedding
The Skip-gram Model
Building the Graph
Training the Model
Visualizing the Embeddings
Optimizing the Implementation
Text classification with TensorFlow
Automatic Translation (seq2seq)
Text Generation with RNN
Named Entity Extraction with RNNs (Sequence Modeling)
Bidirectional LSTM with Attention
Natural Language Processing Pipelines
Conversational AI
Introduction to the Rasa Framework
Generating Natural Language
Understanding Natural Language
Chatbots
Time Series Processing and Forecasting Elements
Traditional Time Series forecasting with ARIMA Models
Defining Autocorrelation
Understanding the Dickey-Fuller Test
Forecasting with TensorFlow and Keras
Using RNN and LSTM in Time Series Prediction
Validation and Metrics of Time Series Prediction Models
References and Next steps
Structured Activity/Exercises/Case Studies
- Keras Hands-on
- TensorFlow Hands-on
- Using TensorFlow to create an RNN
- Sentiment analysis project
- Natural Language Processing project
Conclusion
Training Materials
All AI For Text, NLP, and Forecasting training students receive comprehensive courseware.
Software Requirements
- Any Windows, Linux, or macOS operating system
- Python 3.x installed (Anaconda bundle recommended)
- An IDE with Python support (Jupyter Notebook, Spyder, or PyCharm Community Edition)
