Machine Learning
The world is made up of complicated interactions, hierarchies and substructures. A lot of times, we want to model these complex systems to observe how they behave and to predict what is going to happen in the near future. That’s where machine learning comes in. Machine learning allows us to build programs that can learn from data and replicate how these complex systems behave . The results from these ‘trained’ programs can be used to make optimal decisions that lead to the highest good for the people involved.
So, what is machine learning exactly?
Machine learning is the training of programs developed by allowing the computer to learn from experience, rather than through manually coding the individual steps. Source
Where can it be applied?
- Natural language processing (NLP): Answering questions; speech recognition; summarizing documents; classifying documents; finding names, dates, etc. in documents; searching for articles mentioning a concept.
- Computer vision: Satellite and drone imagery interpretation (e.g., for disaster resilience); face recognition; image captioning; reading traffic signs; locating pedestrians and vehicles in autonomous vehicles.
- Medicine: Finding anomalies in radiology images, including CT, MRI, and X-ray images; counting features in pathology slides; measuring features in ultrasounds; diagnosing diabetic retinopathy
- Biology: Folding proteins; classifying proteins; many genomics tasks, such as tumor-normal sequencing and classifying clinically actionable genetic mutations; cell classification; analyzing protein/protein interactions.
- Image generation: Colorizing images; increasing image resolution; removing noise from images; converting images to art in the style of famous artists.
- Recommendation systems: Web search; product recommendations; home page layout.
- Playing games: Chess, Go, most Atari video games, and many real-time strategy games.
- Robotics: Handling objects that are challenging to locate (e.g., transparent, shiny, lacking texture) or hard to pick up.
- Other applications: Financial and logistical forecasting, text to speech, and much more...
Source
The purpose of this repository:
This repository contains many micro -projects that beginners can use to learn about the various concepts and techniques in machine learning. All the projects are built using python and Jupyter Notebooks. The folders names depict the ML algorithm used in the projects within the folders and each project contains a text or a README file that describes the problem. I have tried my best to make all the code easily understandable and readable. Happy learning!