INTRODUCTION

Hello! Nice to meet you Name : Derni Ageng Age : 21 Date of Birth : 15 December 1996 Hobby : Playing Badminton Topic : Machine learning in IoT Nationality : Indonesia Home Town : Cibubur, East Jakarta

1. Machine Learning in IoT Main Goal: Present a paper, explain how RNN works, and implementation

Machine Learning Internet of Things

Overview Machine Learning Deep Learning Automatic learning ability on systems, through this ability, System can learn and improve from experience without reprogram. Focuses on development of computer programs that can access data and use it and learn for themselves To improve the function of the system, if there was a change which it will affect the function of the system Deep learning is a Technique for implementing Machine Learning It uses neural networks to learn

RNN(Recurrent Neural Network) Remember the parts of the input and use them to make accurate predictions

Machine Learning Methods Unsupervised machine learning algorithms Semi-supervised machine learning algorithms Reinforcement machine learning algorithms Machine Learning Methods

Supervised machine learning algorithms Learned in the past to new data using labeled examples to predict future events Starting from known training dataset, the learning algorithm produces and inferred function to make predictions

Unsupervised machine learning algorithms  Used when the information used to train is neither classified nor labeled. Study how system can infer a function to describe a hidden structure from unlabeled data

Semi-supervised machine learning algorithms between supervised and unsupervised learning, Able to considerably improve learning accuracy Chose when the acquired labeled data requires skilled and relevant resources in order to train or learn it

Reinforcement machine learning algorithms Allow machines and software agents to automatically determine the ideal behavior within a specific context in order to maximize its performance. learning method that interacts with its environment by producing actions and discovers errors or rewards Trial and error search and delayed reward are the most relevant characteristics of reinforcement learning

Tools TensorFlow : Framework created by Google for creating deep learning models Anaconda