67
1
United Kingdom
1 year of experience
I'm Stanley, a passionate early career data scientist. I am a strong systematic thinker who enjoys applying logical reasoning to find elegant and performant solutions to complex problems. Within artificial intelligence, I'm focused on natural language processing (NLP) primarily. I'm also broadly interested in generative AI, reinforcement learning, robotics and recommendation systems. I'm intrigued by the mind and consciousness and fascinated by neuroscience and philosophy. My preferred tech stack is fastai for model development, jupyter notebooks for experimentation, seaborn for visualisation and gradio for data driven web apps. I'm also familiar with the usual pandas, numpy and matplotlib trio. I code version with git/github and my editor of choice is vscode. I'm open to learning any other toolset required to solve the task.
Prereader is an innovative application developed to help students familiarize themselves with complex texts before reading them. The app uses the extensive contextual understanding of an AI named Claude to extract key and methodological concepts from academic materials. By transforming text into audio, using the googleTextToSpeech python package, students can listen to these ideas before delving into the text, supporting their comprehension. Prereader is designed to deliver information in an unpressurized way, with no need for memorization, reducing the stress of encountering new academic content. A unique feature of Prereader is the provision of an offline audio file. This allows students to utilize the app even without data access, whether they are commuting on public transportation or enjoying a quiet walk outdoors. The application combines the advanced capabilities of Claude, the convenience of the googleTextToSpeech package, and the streamlined efficiency of Streamlit for deployment. In summary, Prereader is a powerful tool aimed at improving comprehension and information retention for students tackling challenging academic materials.