Course Outline


Overview of ParlAI Features and Architecture

  • ParlAI framework
  • Key capabilities and goals
  • Core concepts (agents, messages, teachers, and worlds)

Getting Started with ParlAI for Conversational AI

  • Installation
  • Adding a simple model
  • Simple display data script
  • Validation and testing
  • Tasks
  • Agent training and evaluation
  • Interacting with models

Working with Tasks and Datasets in ParlAI

  • Adding datasets
  • Separating data into sets (train, valid, or test)
  • Using JSON instead of a text file
  • Creating and executing tasks

Exploring Worlds, Sharing, and Batching

  • The concept of Worlds
  • Agent sharing
  • Implementing batching
  • Dynamic batching

Using Torch Generator and Ranker Agents

  • Torch generator agent
  • Torch ranker agent
  • Example models
  • Creating models
  • Training and evaluating models

Adding Built-In and Custom Metrics

  • Standard metrics
  • Adding custom metrics
  • Teacher metrics
  • Agent level metrics (global and local)
  • List of metrics

Speeding up Training Runs in ParlAI

  • Setting a baseline
  • Skip generation command
  • Dynamic batching training command
  • Using FP16 and multiple GPUs
  • Background preprocessing

Exploring Other ParlAI Topics

  • Using and writing mutators
  • Running crowdsourcing tasks
  • Using existing chat services
  • Swapping out transformer subcomponents
  • Running and writing tests
  • ParlAI tips and tricks


Summary and Conclusion


  • Knowledge of Python or other programming languages
  • General understanding of artificial intelligence (AI) concepts


  • Researchers
  • Developers
  14 Hours


Related Courses

Microsoft Bot Framework Fundamentals

  14 hours

Microsoft Bot Framework Composer

  14 hours

Data Analysis with Python, Pandas, and Numpy

  14 hours

Machine Learning with Python and Pandas

  14 hours

Accelerating Python Pandas Workflows with Modin

  14 hours

Scaling Data Analysis with Python and Dask

  14 hours

Developing APIs with Python and FastAPI

  14 hours

FARM (FastAPI, React, and MongoDB) Full Stack Development

  14 hours

Scientific Computing with Python SciPy

  7 hours

Game Development with PyGame

  7 hours

Web application development with Flask

  14 hours

Build REST APIs with Python and Flask

  14 hours

Advanced Flask

  14 hours

GUI Programming with Python and Tkinter

  14 hours

Kivy: Building Android Apps with Python

  7 hours