Learn essential deep learning techniques for time-series analysis in manufacturing with this 5-day course. Use low-code development tools to analyze, forecast, and apply deep learning models like ANN, MLP, RNN, and LSTM to improve efficiency and productivity in smart factories.
The Level 2 Deep Learning Essentials for Smart Factory program is a hands-on, 5-day course designed to introduce participants to deep learning technologies and their applications in manufacturing. Focusing on time-series data analysis, this program equips participants with the skills to leverage artificial intelligence (AI) for data-driven decision-making and process optimization in smart factories.
Time-Series Data Analysis: Learn how to clean and visualize time-series data to identify trends, seasonality, and anomalies relevant to manufacturing processes.
Forecasting with Machine Learning: Apply machine learning techniques like ARIMA to predict future values in time-series data, enabling proactive manufacturing decisions.
Deep Learning Model Implementation: Gain practical experience implementing deep learning models such as Artificial Neural Networks (ANN), Multi-Layer Perceptrons (MLP), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) to forecast and analyze time-series data.
Real-World Applications in Manufacturing: Apply your deep learning knowledge to solve real-world manufacturing challenges, driving improvements in production efficiency, quality control, and decision-making.
Managers, engineers, data engineers, data scientists, data analysts, data operations professionals, and AI engineers working in manufacturing or interested in implementing deep learning technologies.
Successful completion of SHRDC Data Analytics Essentials (DAE) or a background in computer science, mathematics, statistics, engineering, business, or accounting.
5 Days
Participants are exposed to theoretical fundamentals and demonstrations of information technology related followed by hands-on activities to support application of competencies acquired.
Analyse time-series data by performing data cleaning, data visualization to identify trends, seasonality, and anomalies from time-series datasets.
Forecast by applying machine learning techniques like ARIMA to predict future values in time series data relevant to manufacturing processes.
Implement deep learning models for time-series analysis by applying concepts regarding Artificial Neural Network (ANN), Mult-Layer Perceptron (MLP), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) to make forecast on time-series data.
Apply time series analysis to solve real-world manufacturing challenges by deploying machine learning & deep learning solutions within participants’ industries, leading to data-driven improvements in production efficiency, quality control and decision-making.
