Anix LynchProanixblog.hashnode.dev·Nov 12, 2024Prompt Engineering Essentials: LangChain's Prompt, Few-Shot, and Output ParsersPrompt engineering centers around designing the input (the "prompt") to make large language models (LLMs) produce the most useful, accurate, and tailored responses. In essence, prompt engineering includes: Prompt Templates: Defining a "template" for...Discuss#PromptEngineering
HowAiWorksblog.howai.works·Oct 21, 2024Machine LearningArtificial intelligence has been the subject of much hype in recent years. The reason for this is the progress made in the field of machine learning. This article gives an overview of the topic and is suitable for beginners and advanced users. Types ...Discuss·35 readsMachine Learning
Sam Schneiderblog.samschneider.me·Aug 7, 2024In a Few Words, What is Few-shot Learning?Imagine that you went to high school in a place where everyone was rich except for you. Your parents had very mediocre jobs, enough to put food on the table and pay for school fees but nothing else. Further imagine that you didn't want anyone else to...Discussfinetuning
Sam Schneiderblog.samschneider.me·Aug 5, 2024Sassy Food Service Bot. Careful. Few-shot Learning is PowerfulMost AIs are almost annoyingly polite. I wondered how easy it would be to make a chatbot that delights in giving sass to customers. Well, turns out just 3 few-shot learning examples was enough. Don't try this at work kids! First, get set up with a Ju...Discuss·60 readsfew shot learning
Sam Schneiderblog.samschneider.me·Aug 1, 2024Why Would You Ever Fine-tune an LLM?You can get pretty good results with few-shot prompt templates, why would you go to the trouble of spending expensive GPU hours to fine-tune an LLM with essentially the same process as few-shot prompt templates? It basically comes down to data. How m...Discussfinetuning
Venkat Rvenkatr.hashnode.dev·Jul 27, 2024Learning from Less Data and Building Smaller ModelsLearning from Less Data: Techniques and Applications Introduction In the age of big data, machine learning models typically need large datasets to perform well. However, gathering and labeling vast amounts of data can be tough and costly. Data-effici...DiscussActive Learning
Venkat Rvenkatr.hashnode.dev·Jun 28, 2024Neural Networks Demystified: From Basics to Advanced ArchitecturesNeural networks are the backbone of modern AI, powering advancements in various fields from image recognition to natural language processing. This blog post will unravel the complexities of neural networks, covering their basics, advanced architectur...Discuss·28 readsArtificial Neurons
William Stetarcopin43.hashnode.dev·Apr 15, 2024Unconventional Metrics for LLMsMy last blog entry introduced an unconventional method to judge models based on their grasp of Samuel Beckett's absurdist play, "Waiting for Godot." We delved into how different LLMs, including GPT-4, handle the play's abstract themes and narrative s...Discusschain of thought
Deepam Mindaminda.hashnode.dev·Feb 25, 2024Few Shot LearningIf you aren’t already familiar with it, few-shot learning (FSL) is an exciting concept in machine learning that focuses on training models to make accurate predictions or classifications when provided with only a very limited amount of labeled data f...Discusslow training data
Jay Galagalacodes.hashnode.dev·Sep 6, 2023Siamese Networks for One-shot LearningI have been working with Siamese Networks a lot in the past few months so I decided to write some articles on it that I would've liked to read the first time I got introduced to the topic. First, we will discuss Siamese networks in general and then h...Discuss·10 likes·142 readsFew shot learningfew shot learning
