Portfolio

Identifying and classifying entities in natural language into predefined categories such as names, locations, organizations, and numerical expressions. NER capable models are able to analyze the context and semantic nuances in the corpus to determine the appropriate category for each entity.

Requires a model to categorize data points into one of two possible categories and the goal is to accurately assign each data point to the correct category.

Refers to the process of determining the degree of similarity between two or more items. In the context of AI, this technique is commonly used to analyze and compare textual data, such as documents, articles, or social media posts. By identifying the similarities between different pieces of content, AI systems can extract valuable insights and patterns.

A type of task where an algorithm is trained to generate an output image from a given input image. This can involve tasks such as image colorization, style transfer, photo processing, or even image-to-image translation where the goal is to transform an image from one domain to another.

In this task diverse machine learning algorithms may be used to analyze a text and then creating a visual representation of the content. Through diffussion (mainly) diverse range and types of visual representations can be created and refined

This task is normally mono modal and typically involves using machine learning algorithms to analyze audio data and identify spoken words, then converting those words into text using natural language processing techniques.