Deep Generative Models

Generative models are forms of Artificial Intelligence (AI) and Machine Learning (ML) that use deep neural networks that understand the distribution of complex training data sets. This knowledge facilitates the generation of large datasets that know the probability of the next item in a sequence. Applications include natural language processing, speech processing, and computer vision.

Why are Deep Generative Models Important?

Deep Generative Models are important in cases where you need more plausible or authentic generated data. Because these models are deeply aware of the underlying distribution and probability inherent in the training dataset, they can synthesize similar datasets.

How Do Deep Generative Models Work?

To create more authentic output from your generative model, you can use Generative Adversarial Networks (GAN) to create a synthetic training data set that trains a second competing Neural Network. The generated neural network instances become negative training examples for the discriminator. By learning to distinguish the generator’s fake data from actual data, generating more plausible and original new data is possible.

Examples of Deep Learning Algorithms

Different algorithms are applicable depending on the application of a deep generative model. These include the following.

Variational Autoencoders

Variational autoencoders can learn to reconstruct and generate new samples from a provided dataset. By utilizing a latent space, variational autoencoders can represent data continuously and smoothly. This enables the generation of variations of the input data with smooth transitions.

Generative Adversarial Networks

Generative adversarial networks (GANs) are generative models that can create new data instances similar to but not the same as the training data sets. GANs are great for creating images but not as sophisticated as diffusion models.

Autoregressive Models

An autoregressive model is a statistical model used to understand and predict future values in a time series based on past values.

Normalizing Flow Models

Normalizing Flows is a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying the rule for change of variables, the initial density ‘flows’ through the sequence of invertible mappings.

Energy-Based Models

An energy-based model is a generative model usually used in statistical physics. After learning the data distribution of a training data set, the generative model can produce other datasets matching the data distributions.

Score-Based Models

Score-based generative models estimate the scores from the training data, allowing the model to navigate the data space according to the learned distribution and generate similar new data.

Applications of Deep Generative Models

Below are some use cases for deep generative models being applied in the real world today:

• Autonomous vehicle systems use inputs from visual and Lidar sensors fed to a neural network that predicts future behavior to make proactive course corrections thousands of times a second.
• Fraud detection compares historical behavior to current transactions to detect anomalies and act accordingly.
• Virtual assistants learn a person’s taste in music, their schedule, purchasing history and any other information they have access to make recommendations. For example, it can provide travel times to home or places to work.
• Entertainment systems can recommend movies based on past viewing of similar content.
• A smartwatch can warn of potential medical conditions, over-exertion, and lack of sleep to oversee the owner’s well-being.
• Images taken with a digital camera or scanned images can be enhanced by increasing sharpness, balancing colors, and suggesting crops.
• Captions can be auto-generated for movies or meeting videos to enhance playback.
• Handwriting style can be learned, and new text can be generated in the same style.
• Captioned videos can have captions generated in multiple languages.
• Photo libraries can be tagged with descriptions to make finding similar ones or duplicates easier.

The Actian Data Platform

The Actian Data Platform provides a unified experience for ingesting, transforming, analyzing, and storing data. The Actian Data Platform provides ultra-fast query performance, even for complex workloads, without tuning using vector processing.