From fraud and security threat detection to flagging abnormalities in healthcare imaging data, there are countless business applications for automatic identification of abnormal data. This process can be challenging, especially when working with large, complex data. This talk explores deep learning approaches (Sequence models, VAEs, GANs) for anomaly detection, when to use them, performance benchmarks and product possibilities.
Why and when to use deep learning for anomaly detection
In-depth coverage of various deep learning models approaches and how they can be applied for anomaly detection
Performance benchmark for various deep learning models for a given dataset
Example use cases, product possibilities, and best practices.
We’ll also address common challenges associated with a lack of labeled anomalous samples or the sheer variety of samples in this space by exploring and demonstrating the performance of unsupervised learning approaches.