Shelf Blog: AI Education

We encounter content chunks every day. Think of a recipe. A recipe contains content components like a title, a list of ingredients, cooking times, pictures of food, and instructions that contain individual steps. These are “chunks” that together compose a recipe. The process of chunking this...

Natural Language Processing (NLP) is an interdisciplinary field blending computer science, artificial intelligence, and linguistics, aimed at enabling computers to understand, interpret, and engage with human language in both written and spoken forms. NLP combines computational linguistics with...

The field of Natural Language Processing (NLP) has witnessed significant advancements, yet it continues to face notable challenges and considerations. These obstacles not only highlight the complexity of human language but also underscore the need for careful and responsible development of NLP...

Can we really trust Artificial Intelligence? Let’s face it. AI has trust issues. AI is rapidly permeating our lives. But perhaps even more rapidly permeating, are fears about AI. Fears that are largely due to a lack of transparency as to how AI works. These concerns are evident in questions people...

What Is Bias in AI? In the realm of artificial intelligence (AI), bias is an anomaly that skews outcomes, often reflecting societal inequities. AI bias can originate from various sources, including the data used to train AI models, the design of algorithms themselves, and the way results are...

The effectiveness of AI implementations, such as generative AI, is intrinsically linked to the quality and structure of the underlying data. However, maintaining the relevance and quality of this data is not a one-time task. It requires a continuous improvement approach, where machine learning...

In machine learning, embeddings are a technique used to represent complex, high-dimensional data like words, sentences, or even entire documents in a more manageable, lower-dimensional space. An analogy would be nice. Right. Think about Lego bricks. A lot of them. High-dimensional data is like the...

We need more than just artificial intelligence. We need virtual experts that are accurate, authoritative, and effective. It’s not enough to deploy AI technologies to answer customer service questions, assist a doctor’s medical diagnosis, identify a negotiator’s key clauses in a contract, provide...

Semantic search goes far beyond the words that people use in their searches, to interpret the intent behind the words, and the greater context in which people are asking. Traditional lexical or keyword-based technologies cannot accomplish this. The relevance and actionability of information that...

Large language models analyze datasets to derive patterns and rules as a method of learning and replicating human intelligence. As you can probably guess, the dataset used in a model can dramatically alter its understanding. We’ve used a number of analogies to explain the significance of this, but it boils down to the same principle: the inputs in LLMs greatly influence the outputs.

Large language models are a type of artificial intelligence (AI) infrastructure used to generate human-like text-based content based on the input they receive.