Jakub Tomczak

I am an assistant professor of Artificial Intelligence in the Computational Intelligence group (led by Prof. A.E. Eiben) at Vrije Universiteit Amsterdam. My main research interests include deep learning, Bayesian inference and deep generative modeling.

2021-09-29



image
Introduction to deep generative modeling: Generative Adversarial Networks (GANs)

In this blogpost, I explain the following:
- What are density networks.
- How to formulate the adversarial optimization problem.
- How to implement GANs.
Full blogpost: READ MORE

2021-09-13



image
Introduction to deep generative modeling: Energy-based Models

In this blogpost, I explain the following:
- How to construction an energy-based model.
- How to implement the Langevin dynamics.
- What are the potential problems with these models.
Full blogpost: READ MORE

2021-08-30



image
Introduction to deep generative modeling: Diffusion-based Deep Generative Models

In this blogpost, I explain the following:
- How to construction hierarchical VAEs with duffiusion-based encoders.
- How to implement diffusion-based DGMS.
- What are recent developments in diffusion-based DGMs.
Full blogpost: READ MORE

2021-08-16



image
Introduction to deep generative modeling: Hierarchical VAEs

In this blogpost, I explain the following:
- Why we use hierarchical latent variable models.
- How to construction hierarchical VAEs.
- How to implement top-down VAEs
Full blogpost: READ MORE

2021-06-16



image
Introduction to deep generative modeling: Neural Compression

In this blogpost, I explain the following:
- What is image compression.
- What is neural compression.
- How to use deep generetive modeling for neural compression
Full blogpost: READ MORE

2021-04-8



image
Introduction to deep generative modeling: Priors in VAEs

In this blogpost, I explain the following:
- How to re-write the ELBO in VAEs.
- Why priors are so important.
- How to model priors using Mixture of Gaussians, VampPriors, GTMs and flows!
Full blogpost: READ MORE

2021-03-24



image
Introduction to deep generative modeling: Hybrid modeling

In this blogpost, I explain the following:
- How to train the joint distribution p(x,y).
- How we can make it work.
- How to implement your own hybrid model with IDFs!
Full blogpost: READ MORE

2021-03-11



image
Introduction to deep generative modeling: Integer Discrete Flows

In this blogpost, I explain the following:
- What is a potential problem with continous variables.
- How we can learn a distribution over integer-valued variables.
- How to implement your own Integer Discrete Flows!
Full blogpost: READ MORE

2021-02-23



image
Introduction to deep generative modeling: Variational Auto-Encoders

In this blogpost, I explain the following:
- What is a latent variable model.
- How we can learn non-linear latent variable models efficiently (e.g., by using variational inference).
- How to implement your own Variational Auto-Encoder!
Full blogpost: READ MORE

2021-02-08



image
Introduction to deep generative modeling: Flow-based models

In this blogpost, I explain the following:
- What is a flow-based model.
- How we can parameterize a flow-based model using invertible neural networks.
- How to implement your own flow-based model using coupling layers!
Full blogpost: READ MORE

2021-01-25



image
Introduction to deep generative modeling: Deep Autoregressive Models

In this blogpost, I explain the following:
- What is an autoregressive model.
- How we can parameterize an autoregressive model using various neural networks.
- How to implement your own autoregressive model using causal convolutions!
Full blogpost: READ MORE

2021-01-11



image
Introduction to deep generative modeling: Why, Where and How

In this blogpost, I answer three questions:
- Why do we need deep generative modeling?
- Where do we use deep generative modeling?
- How do we formulate deep generative models?
Full blogpost: READ MORE