Course Overview
This will be a more advanced exploration of the libraries that developers will have been exposed to, deep learning, additional models, operationalization concerns of these systems, and the often-forgotten security aspects of data-driven systems. The goal will be to have as many hands-on activities as is feasible intermixed with a sufficient amount of theory to motivate the exercises.
Who should attend
- Data Engineers
- Software Developers
- Machine Learning Engineers
Outline: Advanced Data Science & Machine Learning (ADSML)
Deeper Data-Engineering Dives
- SQL
- Advanced Numpy
- Advanced Pandas
- Advanced Visualization
Deeper Deep Learning Dives
- Keras and PyTorch
- CNNs
- Generative Models
- PyTorch Lightning
- Model Exchange with ONNX
Additional Models
- Time Series Data
- Classical Time Series Models
- RNNs, LSTMs
- PyTorch Forecasting
- Anomaly Detection
- Ranking Models
- Metrics
- Models
- Multi-Modal Models
- Representation
- Alignment
- Composaibility of Models
- Modality Transference
- Quantification
- Multimodal Framework (MMF)
- NLP Models
- Embeddings
- Transformers
- LMM and ChatGPT
MLOps and Security
- Data Engineering Pipelines
- Apache Airflow
- Deployment Architectures
- Continuous Learning
- Handling Streaming Data
- Security
- Threat Taxonomies
- Monitoring, Logging, and Alerting