Course Overviews

Learn about the applications of AI and machine learning technology in the veterinary space and where you will encounter it. Establish a grounding understanding of the importance of data in the world of machine learning, the need for quality data and how it is generated, and what this all means to you as a practitioner. 

​

Lesson 1: Industry overview and why we should care (6:20)

Discusses where AI tools can be used in the veterinary industry now and in the future. Describes the critical importance of engaging in AI technology development early in the adoption period into the veterinary industry.

​

Lesson 2: Data Pre-processing: Fundamentals (8:55)

Discusses the importance of good quality data for effective machine learning, and the process used to create a dataset that is useful for machine learning. Introduces questions about source data that AI tool users should ask of their tool providers to assess tool reliability. 

​

Lesson 3: Data Preprocessing: Privacy and Bias (12:52)

Introduces data privacy regulations and how they affect veterinary clinic responsibilities in client communication. Discusses data bias and explores how it may affect tool usefulness. Introduces questions for AI tool users to ask themselves about potential for data bias when using AI tools for decision making.  

Explore about the fundamental reasoning and building blocks of machine learning, understand the benefits of machine learning and how different models of machine learning provide both advantages and disadvantages. Discuss the implications of using machine learning tools on how you practice and what you should watch out for.

 

Lesson 1: Supervised Machine Learning: The Basics (12:45)

Illustrates the concept of mathematical relationships between features, and the most basic process involved in machine learning. Explains the importance of dataset breakdown into training, verification and test sets for quality control.

 

Lesson 2: Supervised Machine Learning: From Regression to Classification (9:33)

Expands the machine learning process to apply it to classification models and illustrates how algorithms can be used to achieve different goals. Explains how classification models are generated and provides examples of applications in medicine.

 

Lesson 3: Supervised Machine Learning: Decision trees and Random Forests (13:56)

Explains the design of decision trees and random forests and connects this with the advantages and disadvantages of these models. Emphasizes the  variety of machine learning models and the flexibility found in their diversity.

Discover how neural networks operate and how different forms of neural networks provide different benefits. Appreciate the power of neural networks and how they are moving veterinary science and practice forward, explore how neural networks are being used in practice, and continue to grow your awareness of pitfalls to watch out for when using neural networks. Learn about large language models and how to prompt ChatGPT so it can work for you effectively. 

​

Lesson 1: Neural Networks, The Basics (14:38)

Describes the fundamental building blocks of neural networks and uses intuitive examples to illustrate how they work. By breaking down the network structure into understandable components, this lesson showcases the strengths, flexibility and computing power of neural networks.

​

Lesson 2: Convolutional Neural Networks (14:31)

Illustrates how images are converted into data suitable to be used in neural networks, and how that data is then processed by CNN’s. Using examples from current scientific journals, this lesson highlights current applications of CNN’s. Explains potential CNN model drawbacks and their implications to practitioners using CNN-based assistive tools.

​

Lesson 3: Recurrent Neural Networks (17:29)

Breaks down the unique model structure of RNN’s that allows them to process sequential data by tracing the flow of data through the neural network. Highlights the wide range of applications for RNN’s, with examples cited from current scientific journals. Concludes with a summary of the weaknesses of RNN’s and how these may affect practitioners’ choices when using them.  

​

Lesson 4: Unsupervised Machine Learning: Large Language Models and Chat GPT (23:39)

Provides a broad definition of unsupervised machine learning followed by a description of what foundational large language models are, how they are trained and how they are used. Focuses on ChatGPT as an example of a practical user interface with LLM’s. Teaches, with examples, a step-by-step prompting method to maximize useful GPT outputs. Closes with descriptions of drawbacks and risks of generative AI text based tools to allow practitioners to make informed decisions on their use.