Original article can be found here (source): Deep Learning on Medium
Understanding the difference between Data Science, AI, ML and Deep Learning?
Data science translates data into tangible business value. AI, ML and Deep learning help derive insightful information from the data but it is the data science aspect that turns it into meaningful information so that companies can make better decisions. For instance, a business (e.g. fashion retail company) that is looking to increase their revenue can employ machine learning techniques that can help them answer questions such as what is the latest trend, how can we target specific customers and at what price-range are consumers more likely to buy a particular product.
Understanding three areas – Domain Expertise, Computer Science and Mathematics – can help with answering your problem.
AI mimics the way the human brain works. Machines make connections from which they draw the ability to adapt and learn. Siri, chatbots and handwriting software are all examples of where AI is used.
Machine Learning is a subset of AI. A machine learning algorithm learns from the input data, finds patterns, and predicts an outcome. An example includes, categorising emails into different folders. The algorithm firstly learns how emails are categorised. Then tries to associate words in the email allocated to that particular category and predicts what category a new email should go into as soon as it arrives. Fraud detection is another example where machine learning algorithm can be applied.
Deep Learning is a subset of Machine Learning. It solves problem on a higher complexity level. For example, self-driving cars have sensors and cameras that can detect pedestrians, traffic lights, cars and other objects through complex algorithms.