Introduction to AI and Vector Search
Learn about the foundations of AI and how Atlas Vector Search fits in.
Introduction to AI and Vector Search
Unit Overview
In this unit, you'll learn about the foundations of AI. You'll be able to define key terms such as machine learning, deep learning, and natural language processing. After that, you'll learn the basics of the transformer model which is the foundation of large language models and modern generative AI applications. Finally, we'll dive deeper into the transformer model and learn about the different components that generate the embeddings used in Atlas Vector Search.
Prerequisites
- Getting Started with MongoDB Atlas
- MongoDB Aggregation
- MongoDB Indexes
- Introduction to Atlas Search
- Analyzers in Atlas Search
Lessons in This Unit
- Lesson 1 – Introduction to AI
- Lesson 2 – A Brief History of Models
- Lesson 3 – Sequence to Sequence Models, Encoders, and Decoders
Parker Faucher | University Curriculum Engineer
Parker is a Curriculum Engineer on the Education team at MongoDB. Prior to joining MongoDB, he helped maintain a world class developer bootcamp that was offered in multiple universities. He is a self taught developer who loves being able to give back to the community that has helped him so much.
Katie Redmiles | Curriculum Designer
Katie is a Curriculum Designer at MongoDB. Before joining the Curriculum team, Katie worked on the University Enablement team developing Learning Bytes and instructional materials for the MongoDB for Academia program. Katie also worked within the Digital Learning Division at the Foreign Service Institute where she honed her skills at developing online learning for a global audience. Katie is passionate about making education accessible and engaging for everyone.
Vick Mena | Director, Curriculum
My name is Vick and I've been in the wild for over 25 years. I grew up at IBM working on the BIOS for the IBM eServer line in Austin, TX before moving to Wall St. I've worked on all phases of software development from low-level to middleware to UI but feel most comfortable in the middle. I also drank the devops kool-aid having moved a product line to AWS while at Dow Jones & Co with the help of an amazing team. I then pivoted into the secure space and worked on software/hardware reverse engineering. I always thought I'd eventually teach and this role lets me leverage all of my experience to lead this motley crew of passionate educators.
Emily Pope | Senior Curriculum Designer
Emily is a Senior Curriculum Designer at MongoDB. Prior to MongoDB, Emily worked closely with professors at MIT and Columbia to design bootcamps in full stack development and data science at Emeritus. She also worked as an instructional designer on database and computer science learning experiences at Cengage. Emily loves learning about the everchanging tech space and is passionate about making these skills accessible to a global audience.
Welcome! In this unit we’ll explore the artificial intelligence ecosystem to better understand where Atlas Vector Search fits in. My name is Katie
Artificial Intelligence has been an important topic lately with the release of OpenAI’s ChatGPT. It seems like almost every day we see the release of some cool AI tool that is going to change our lives.
While AI as a technology is a product of the 20th and 21st centuries, its conceptual roots can be traced back to ancient times.
It originates in ideas that go all the way back to the Greek philosopher Aristotle, like when he described the means-ends analysis in Nicomachean Ethics.
The means-ends analysis is a process for problem solving.
It declares that when you have a current state and a goal state you should take actions that reduce the difference between the two.
While Aristotle was millennia away from developing an intelligent machine, his logic laid the groundwork that would be built upon over centuries.
Now let’s fast forward about two thousand years so this doesn't turn into a history course.
In the 1950s a scientist named Alan Turing, who is widely regarded as one of the fathers of AI, introduced the Turing Test.
The Turing test was an exercise that included a person, a machine, and another person who acts as a judge.
The judge would read a conversation between the person and the machine.
Knowing the conversation included a machine and a person, the judge would have to identify the machine.
If the judge couldn’t distinguish the machine from the person then the machine passed the Turing test.
At the time, this seemed out of the realm of possibility.
But that didn’t deter people from trying.
Shortly after, the term Artificial Intelligence was coined by John McCarthy who went on to create the MIT AI Lab.
In the 1960s, a researcher from the MIT AI Lab named Joseph Weizenbaum created ELIZA, the first chatbot.
ELIZA would take on the persona of a psychotherapist and perform an initial psychiatric interview.
ELIZA would examine text for keywords, assign values to them, and transform the input to output.
This isn’t too different from how chatbots work today.
With each passing decade, we continued to see massive developments in Machine Learning, Natural Language Processing, and AI in general.
As computers improved, so did AI. Many people had the chance to see this first-hand when IBM’s Watson took on some of the best Jeopardy players and beat them.
Then in 2017, AI took a huge leap forward when researchers from Google first described the Transformer model in the “Attention Is All You Need” paper.
The transformer model is now used in almost every Generative AI product you see, whether it’s ChatGPT, Gemini, Copilot, or anything in between.
In this unit, we’ll dive deeper into Artificial Intelligence by first learning about the different components of AI.
After that, we’ll take a brief history lesson on neural networks and how they have improved.
Finally, we’ll explore the different ways the Transformer model can be used.
By the end of this unit, you'll have a foundational understanding of what AI is. This knowledge will prepare you to learn even more about the AI space so you can implement AI in your own application.
Alright, let’s get started!
