Embedding

This course is designed to provide a deep understanding of embeddings, a powerful unsupervised learning technique, with a focus on its applications in Production Control and Operations (P&OC). Participants will learn how to represent complex data structures, such as time series, graphs, and text, in a lower-dimensional space while preserving their semantic relationships. The course covers various embedding techniques and their applications in production scheduling, inventory management, and supply chain optimization.

• Understand the concept of embeddings and their applications in Production Control and Operations

• Implement and evaluate various embedding techniques for time series, graphs, and text data in P&OC contexts

• Apply embeddings to solve production scheduling, inventory management, and supply chain optimization tasks

• Utilize graph embeddings for workflow analysis and resource allocation in production systems

• Leverage text embeddings for sentiment analysis and document classification in P&OC-related data

1. Introduction to Embeddings in P&OC

• Overview of embeddings and their role in unsupervised learning

• Applications of embeddings in Production Control and Operations

• Vector space models and their properties

• Hands-on exercises: Implementing basic embedding techniques (e.g., one-hot encoding, bag-of-words) for P&OC data

2. Time Series Embeddings in P&OC

• Time series data in Production Control and Operations (e.g., demand forecasts, production schedules)

• Time series embedding techniques (e.g., Dynamic Time Warping, Time Series Kernels)

• Deep learning approaches for time series embeddings (e.g., Recurrent Autoencoders, Temporal Convolutional Networks)

• Applications of time series embeddings in P&OC (e.g., production scheduling, inventory management)

• Hands-on exercises: Developing a time series embedding model for P&OC time series data

3. Graph Embeddings in P&OC

• Introduction to graph theory and network analysis in production systems

• Random walk-based embeddings (DeepWalk, node2vec) for production workflow analysis

• Matrix factorization-based embeddings (Laplacian Eigenmaps, Graph Factorization) for resource allocation and constraint optimization

• Applications of graph embeddings in P&OC (e.g., supply chain optimization, facility layout planning)

• Hands-on exercises: Implementing graph embedding techniques on P&OC network data

4. Text Embeddings and Applications in P&OC

• Text data in Production Control and Operations (e.g., work orders, quality reports)

• Word embeddings (Word2Vec, GloVe, FastText) for sentiment analysis in P&OC-related text data

• Document embeddings (Doc2Vec, TF-IDF) for document classification and clustering in P&OC

• Contextualized embeddings (ELMo, BERT) for named entity recognition and relation extraction in production control and operations text data

• Hands-on exercises: Applying text embedding techniques to solve a real-world P&OC problem

• Solid understanding of linear algebra, calculus, and probability theory

• Proficiency in programming with Python, including experience with deep learning frameworks (e.g., TensorFlow, PyTorch)

• Familiarity with unsupervised learning concepts and dimensionality reduction techniques

• Knowledge of production control and operations management principles