Deep Learning for Anomaly Detection
From fraud detection to flagging abnormalities in imaging data, there are countless applications for automatic identification of abnormal data. This process can be challenging, especially when working with large, complex data. This report explores deep learning approaches (sequence models, VAEs, GANs) for anomaly detection, when to use them, performance benchmarks, and product possibilities.
Transfer Learning for NLP
Natural language processing (NLP) technologies can translate language, answer questions, and generate human-like text, but the underlying deep learning techniques require costly datasets, infrastructure, and expertise. In this report, we show how to use transfer learning to adapt existing models to any NLP application, making it easier to build high-performance NLP systems.
Deep Learning for Image Analysis - 2019 Edition
Convolutional neural networks (CNNs or ConvNets) excel at learning meaningful representations of features and concepts within images, making CNNs valuable for solving problems in multiple domains, from medical imaging to manufacturing. In this report, we show how to select the right deep learning models for image analysis tasks and techniques for debugging deep learning models.
Learning with Limited Labeled Data
In this report, we focus on learning with limited labeled data, a collaborative approach between human and machines that reduces the amount of labeled data typically required by supervised machine learning yet performs comparably.
In this report, we focus on federated learning, an approach for training machine learning models on distributed edge node data while ensuring privacy and minimizing communication costs.
In this report, we focus on multi-task learning, a new approach to machine learning that allows algorithms to master tasks in parallel.
In this report, we show how using the semantic content of items can help solve common recommendation pitfalls such as the cold start problem, and open up new product possibilities.
In this report, we show how to make models interpretable without sacrificing their capabilities or accuracy.
Here, we show how to use probabilistic programming and Bayesian inference to easily build tools that make better predictions for more effective decision making.
Learn how to use deep learning and embeddings to make text computable for a variety of business applications and products.
Deep learning: Image analysis
This report explores the history and current state of deep learning, explains how to apply it, and predicts future developments.
Probabilistic methods for realtime streams
Here, we explore probabilistic methods that offer highly efficient models for extracting value from streams of data as they are generated.
Natural language generation
In this report, we look at how machine systems can turn highly structured data into human language narrative.
Read the Fast Forward Labs blog
Privacy, data governance, and machine learning: the regulatory perspectiveWhy do privacy and governance matter?...
Keep up with tomorrow
Sign up for our monthly newsletter and get the latest on advances in applied artificial intelligence, as well as company news and events.