{"id":3011,"date":"2019-05-29T23:26:31","date_gmt":"2019-05-29T21:26:31","guid":{"rendered":"https:\/\/blogs.mathworks.com\/student-lounge\/?p=3011"},"modified":"2025-03-04T08:54:44","modified_gmt":"2025-03-04T13:54:44","slug":"deep-learning-for-student-competitions","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/student-lounge\/2019\/05\/29\/deep-learning-for-student-competitions\/","title":{"rendered":"Deep Learning for Student Competitions"},"content":{"rendered":"

In today\u2019s post, Neha Goel<\/a> is going to share an overview about how you can use MATLAB and Simulink for Developing Artificial Intelligent components in your competitions<\/em>. Neha joined the team recently and focuses on deep learning and data science competitions. Also find a section in this post where Neha reveals what projects she is currently working on.<\/p>\n

—<\/p>\n

Competitions and students in different application areas are adding AI components to their projects. The major areas include Autonomous Vehicle Competitions, Aerospace, Robotics, Data Science etc.\u00a0 Refer to link here<\/a> to know about all competitions MathWorks sponsors.<\/p>\n

Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) are some of the hottest topics right now. In this post we will give you a high-level overview of how you can implement these in your projects depending on the type of data you are working with. We will also be directing you to resources for learning how to implement AI in MATLAB.<\/p>\n

\"\"<\/a><\/p>\n

Source: <\/em>Legal Executive Institute<\/em><\/a><\/p>\n

Technology and Terminology<\/h1>\n

The first step towards understanding Deep Learning and how it works is to grasp the differences between important terms.<\/p>\n

\"\"<\/a><\/p>\n

Source: <\/em>Difference between AI, Machine Learning & Deep Learning<\/em><\/a><\/p>\n

Artificial Intelligence<\/strong> <\/span>\u2013 the replication of human intelligence in computers.<\/p>\n

In the words of the person who coined the term artificial intelligence, John McCarthy, \u201cIt is the science and engineering of making intelligent machines\u201d.<\/p>\n

A common application of AI is Search Engine Algorithm.\u00a0It is a way to exhaustively check through many (or even all) possible outcomes using a model of the environment. There’s no learning component since you don’t need any experience\/data to do this!<\/p>\n

Machine Learning<\/strong><\/span> – referring to the ability of a machine to learn using\u00a0\u00a0data sets instead of hard coded rules.<\/p>\n

Machine Learning allows computers to learn by themselves. This type of learning takes advantage of the processing power of modern computers, which can easily process large data sets.<\/p>\n

\"\"<\/a><\/p>\n

Source: Next-Gen Talk by Sebastian Raschka<\/a><\/em><\/p>\n

Unsupervised Learning –\u00a0<\/strong><\/span>the task of machine learning using data sets with no specified structure.<\/p>\n

When training an algorithm using unsupervised learning, the algorithm will classify itself automatically.<\/p>\n

An example of unsupervised learning is a behavior-predicting AI for an e-commerce website. The algorithm won\u2019t learn by using a labelled data set of inputs and outputs. It will recommend related items based on the historical data. The grouping is strictly based on what the algorithm has learned.<\/p>\n

Supervised Learning<\/strong><\/span>– involves using labelled data sets that have inputs and expected outputs.<\/p>\n

When you train using supervised learning,\u00a0 an input and an expected output are provided for the algorithm in advance. If the output generated by the program is wrong, it will readjust its calculations. This process is done iteratively over the data set, until the algorithm is optimized.<\/p>\n

An example of supervised learning is a weather-predicting AI. It learns to predict weather using historical data. That training data has inputs (humidity, wind speed, temperature) and outputs (chance of rain).<\/p>\n

Reinforcement Learning\u00a0<\/span><\/strong>(RL) –\u00a0 an area of machine learning concerned with how software agents ought to take actions in an environment to maximize<\/p>\n

It differs from supervised learning in that labelled input\/output pairs need not be presented, and sub-optimal actions need not be explicitly corrected. Instead the focus is finding a balance between exploration (of uncharted territory) and exploitation (of current knowledge) to try learning optimal behavior.<\/p>\n

\"\"<\/a><\/p>\n

Source: <\/em>Wikipedia \u2013 Reinforcement Learning<\/em><\/a><\/p>\n

Reinforcement Learning is best explained with the above diagram. An agent takes actions in an environment, which is interpreted into a reward and a representation of the state, which are fed back into the agent.<\/p>\n

Reinforcement learning is used in operations research,\u00a0Operations research, control theory, multi-agent systems, information theory, game theory, simulation-based optimization, and more.<\/p>\n

Check out the below links to know more about MATLAB Reinforcement Learning Toolbox and examples<\/p>\n