Machine Learning for Lawyers (Understanding)

Overview

Machine Learning and AI are the next big wave in technology. And yet, one does not have to be a technical expert to understand the inputs and outputs of ML.

This course is intended for lawyers, legal support, and IT. Its goal is to explain the capabilities and limitations of ML. No coding is required, but the labs and exercises will assure that the attendants will grasp and retain the major principles and ideas.

The course maintains an optimal balance of theory and practice. For each machine learning concept, we first discuss the foundations, its applicability, and limitations. Then we explain the implementation and use, and specific use cases. The course consists of 50% lecture, 50% lab work.

This course is taught by Mark Kerzner, who is an expert in Machine Learning and eDiscovery. Mark has taught and consulted in law firms and legal technology companies.

Objectives

  • Attain a thorough understanding of popular machine learning algorithms, their applicability, and limitations
  • Practice the application of these methods with the tools of choice
  • Achieve clarity in the real-world use of machine learning by illustrating each method with practical use cases

Audience

Lawyers, legal support, IT.

Duration

1 day

Pre-requisites

  • Computer literacy, such as using MS Office

What to Bring

  • A reasonably modern laptop (Need to be able to connect to clusters running on cloud services; corporate laptops with overly restrictive firewalls usually give problems).
  • Working installed tools will be provided in the cloud. Students would only need a browser and optional use of a remote client.
  • Chrome browser with Markdown Preview Plus plugin

Detailed Outline

Introduction

    • Goals and capabilities of Machine Learning
    • Machine learning: goals, types, results
    • What is meant by “training the model”?

Classification

    • Predicting categories
    • Logistic regression
    • Document classification
    • Lab: Building document classifier

Linear regression

    • Predicting a number
    • Use cases for analyzing your business
    • Lab: predicting the size of a case

Naive Bayes

    • Assigning probabilities to an outcome
    • Filtering out irrelevant documents
    • Lab: spam filtering

Decision Trees

    • How to answer a few ‘yes’ or ‘no’ questions to arrive at a decision
    • Lab: predicting case outcome

LDA

    • Making sense of your documents
    • Topic modeling with LDA
    • Lab: find major concerns in the document set

Deep Learning and AI

    • Automatic translation, face recognition, self-driving cars
    • How AI can be applied to specific cases
    • Lab: use document understanding model