By: Festus Ewakaa Kahunla Welcome back to 'The AI Corner', where we delve deep into the fascinating world of artificial intelligence. Today, we uncover a silent champion In the radiant realm of artificial intelligence, where machines mimic human thought and intuition, there lies a quiet but powerful force: web scraping. Just as the River Rokel winds its way through Sierra Leone, nourishing the lands, web scraping meanders through the digital realm, providing the lifeblood for AI The Symphony of Data: Setting the Stage Picture the vibrant Salone festivals, with each musician playing a crucial role in bringing the performance to life. In AI's harmonious world, data forms the rhythm, and web scraping, often overlooked, is akin to the traditional balangi player, extracting essential notes needed for the AI dance. The Cotton Tree of AI: Web Scraping Much like Freetown's historic Cotton Tree stood tall and deep-rooted, web scraping forms the pillar of AI. It sifts...

  By: Festus Kahunla Hello to all our readers from Sierra Leone and beyond! Today, we'll embark on a journey to understand one of the foundational pillars of machine learning: Decision Trees. Let’s dive into this captivating topic with an analogy most of us can relate to. Setting the Scene: Decision-Making in Everyday Life Imagine you’re deciding what to wear today. You peek outside: if it's sunny, you choose a light shirt, but if it's raining, you opt for a raincoat. This type of logic, where you make decisions based on certain conditions, is the essence of Decision Trees in machine learning. What Exactly is a Decision Tree? A Sierra Leonean Tale Imagine you're at a crossroads, with two paths stretching out before you. One path is labeled “Sierra Leone” and is characterized by the familiar sights and sounds of home, filled with both its unique challenges and undeniable beauty. The other path is labeled “America”, paved with golden opportunities, yet also new ch...

By Festus Ewakaa Kahunla The world of Natural Language Processing (NLP) has been buzzing with the advent of Large Language Models (LLMs) that boast billions of parameters. These models, while incredibly powerful, come with their own set of challenges, especially when it comes to deployment and fine-tuning. A recent paper titled "PETALS: Collaborative Inference and Fine-tuning of Large Models" offers a fresh perspective on this issue. Let's dive into the key takeaways from this paper. The Challenge with LLMs Modern LLMs, such as BLOOM-176B, have more than 100 billion parameters. While these models are now available for download, using them requires high-end hardware, which many researchers might not have access to. Techniques like RAM offloading or hosted APIs offer some respite, but they come with their own limitations. For instance, offloading can be slow, and APIs might not offer the flexibility needed for specific research tasks. Introducing PETALS PETALS, a sy...

  The world of artificial intelligence (AI) is constantly evolving, with new models and tools being introduced regularly. One of the latest entrants in this dynamic field is Claude 2, a sophisticated AI model developed by Anthropic, a company dedicated to advancing AI technology. This blog post will delve into the features, capabilities, and potential of Claude 2 as a student buddy, and how it surpasses ChatGPT in this regard. Introducing Claude 2 Claude 2 is the successor to the original Claude model, released in the first quarter of 2023. It's an AI model that has garnered significant attention in the AI community for its impressive capabilities and user-friendly interface. Claude 2 is a powerful large language model (LLM) similar to ChatGPT, but with some unique features that set it apart. Claude 2: A Student's Best Friend One of the standout features of Claude 2 is its enhanced performance compared to its predecessor. It can provide longer responses and summarize nove...

Google's AI language model, Bard, has been making waves in the tech world with its innovative features and capabilities. The recent slew of updates has further enhanced its appeal, making it a versatile tool for various applications. Here's a rundown of the exciting new features and improvements that Bard has rolled out. Global Language Support One of the most significant updates is Bard's expansion into over 40 new languages, including Arabic, Chinese (Simplified/Traditional), M, Hindi, Spanish, and more. This massive expansion has made Bard a truly global tool, enabling users from all corners of the world to explore possibilities and create content in their native languages. Google Lens Integration Bard has integrated Google Lens into its platform, allowing users to upload images alongside text in their conversations. This feature boosts imagination and creativity in completely new ways, making Bard an even more powerful tool for content creation. Text-to-Speech C...

  Welcome to The AI Corner, where we delve into the fascinating world of artificial intelligence. Today, we're exploring a captivating facet of AI known as generative AI . This technology is revolutionizing various industries by creating new, unique content, from text and images to music and even code. What is Generative AI? Generative AI is a subset of artificial intelligence that leverages machine learning models to generate new data. These models are trained on existing data, learning patterns and structures, and then use this knowledge to create new data with similar characteristics. This technology has the potential to significantly impact various industries, from art and entertainment to healthcare and finance. How Does Generative AI Work? Imagine you're trying to teach a child how to draw a cat. You'd probably start by showing them several pictures of cats. Over time, the child begins to understand the common features of a cat - pointy ears, whiskers, a tail - an...

  Just as birds of the same feather flock together, data points in a dataset with similar characteristics tend to cluster together. This is the fundamental idea behind the K Nearest Neighbors (KNN) algorithm, a popular and intuitive method used in machine learning. This blog post aims to explain KNN in a way that is accessible and understandable for everyone. What is K Nearest Neighbors? K Nearest Neighbors, or KNN, is a supervised machine learning algorithm that classifies a data point based on how its neighbors are classified. To illustrate, imagine you're trying to understand a person's character. One way you might do this is by looking at their friends or the group they hang out with. If most of their friends are athletes, you might classify this person as an athlete too. This is similar to how KNN works. However, KNN is considered a lazy learning algorithm, meaning it doesn't immediately generalize from the training data. It waits until it is given a test observati...