Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Resource-Aware Machine Learning in the IoT Era

Description

This lecture covers the main machine learning challenge in the IoT era, focusing on resource-constrained IoT nodes and tiny processors like MSP430F2013. It discusses complex learning algorithms, power breakdown analysis, sleep apnea, and artery-related issues. The lecture also delves into resource-aware classification, featuring low and high-quality complexity classifiers, and event-driven classification inspired by brain efficiency. Additionally, it explores datasets for training, validation, and testing, highlighting the increase in battery lifetime without significant machine-learning performance loss.

In MOOC

IoT Systems and Industrial Applications with Design Thinking

Official source

Related concepts (21)

Genetic algorithm

In computer science and operations research, a genetic algorithm (GA) is a metaheuristic inspired by the process of natural selection that belongs to the larger class of evolutionary algorithms (EA). Genetic algorithms are commonly used to generate high-quality solutions to optimization and search problems by relying on biologically inspired operators such as mutation, crossover and selection. Some examples of GA applications include optimizing decision trees for better performance, solving sudoku puzzles, hyperparameter optimization, causal inference, etc.

Machine learning

Machine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.

Algorithm

In mathematics and computer science, an algorithm (ˈælɡərɪðəm) is a finite sequence of rigorous instructions, typically used to solve a class of specific problems or to perform a computation. Algorithms are used as specifications for performing calculations and data processing. More advanced algorithms can use conditionals to divert the code execution through various routes (referred to as automated decision-making) and deduce valid inferences (referred to as automated reasoning), achieving automation eventually.

Flow battery

A flow battery, or redox flow battery (after reduction–oxidation), is a type of electrochemical cell where chemical energy is provided by two chemical components dissolved in liquids that are pumped through the system on separate sides of a membrane. Ion transfer inside the cell (accompanied by flow of electric current through an external circuit) occurs through the membrane while both liquids circulate in their own respective space. Cell voltage is chemically determined by the Nernst equation and ranges, in practical applications, from 1.

Lithium-ion battery

A lithium-ion or Li-ion battery is a type of rechargeable battery which uses the reversible reduction of lithium ions to store energy. The negative electrode of a conventional lithium-ion cell is typically graphite, a form of carbon. This negative electrode is sometimes called the anode as it acts as an anode during discharge. The positive electrode is typically a metal oxide; the positive electrode is sometimes called the cathode as it acts as a cathode during discharge.

Related lectures (31)

Machine Learning: Fundamentals and Applications

Introduces machine learning basics, covering data segmentation, clustering, classification, and practical applications like image classification and face similarity.

Introduction to Machine Learning

Covers the basics of Machine Learning, including recognizing hand-written digits, supervised classification, decision boundaries, and polynomial curve fitting.

Introduction to Machine Learning

Covers the basics of machine learning for physicists and chemists, focusing on image classification and dataset labeling.

Kohonen Maps: Summary

Summarizes Kohonen maps, covering initialization, sampling, similarity-matching, examples, and applications in machine learning and data classification.

Solving Parity Games in Practice