Our course introduction to deep learning with Jax is now available online at https://github.com/Deep-Learning-with-Jax . The material currently consists of lecture videos, slides and exercises. Most exercises come with unit tests, allowing you to verify your solutions independently.
Category Archives: All Projects
On the similarities of diffused- and gan-generated image detection
Guided diffusion has become the new go-to method for image generation. To avoid misuse of this inspiring new technology, we must ensure fake detection networks remain up to speed with recent developments. Using the approach described in “Diffusion models beat gans on image synthesis”. Wavelet packets decompose an input into blocks according to frequency. The …
Continue reading “On the similarities of diffused- and gan-generated image detection”
Wavelet-Packet Powered Deepfake Image Detection
Modern neural networks generate realistic artificial images and audio. This development will allow us to create movies, music and audio effects never seen before. Yet at the same time, the new technology may enable new digital ways to lie. In response, the need for a diverse and reliable toolbox arises to identify artificial images and …
Continue reading “Wavelet-Packet Powered Deepfake Image Detection”
Wavelet optimization for Network compression
Wavelets are uncommon in machine learning, systems with learnable wavelets, in particular, are rare. Promising applications of wavelets in neural networks exist. Adaptive wavelets for network compression are explored in the new paper ‘Neural network compression via learnable wavelet transforms‘. By defining new wavelet loss terms based on the product filter approach to wavelet design, …
Continue reading “Wavelet optimization for Network compression”
Jaxlets – Fast Wavelet Transformations in JAX
The fast wavelet transform is an important signal processing algorithm. Jet a differentiable implementation in JAX has been missing so far, I have therefore opened my implementation . It supports the one and two dimensional analysis and synthesis transforms. As well as an implementation of the forward wavelet packet transform. The plot below shows an …
Continue reading “Jaxlets – Fast Wavelet Transformations in JAX”
Video Prediction à la Fourier
Video frame prediction is a very challenging problem. Many recent neural network based solution-attempts trained using a mean squared error lead to blurry predictions. My most recent paper currently under review proposes to use Phase correlation and the Fourier-Shift theorem estimate changes and transform current images into predictions. A demo is shown below. The video …
Complex Recurrent Neural Nets
The paper Complex gated recurrent neural networks explores machine learning in the complex domain. For gradient descent to work the functions involved must be differentiable. In the complex domain holomorphic functions, which satisfy the Cauchy-Riemann partial differential equations are differentiable. Finding functions which fulfill this requirement and are useful for machine learning tasks is very …
Spectral-RNN
Fourier methods have a long and proven track record as an excellent tool in data processing. Integrating Fourier methods into complex recurrent neural network architectures is therefore an important goal. I integrated the short-time Fourier transform into a recurrent (complex-valued) network structure. This helps when dealing with hard prediction tasks such as human motion prediction, …
Control Engineering
My favorite control project thus far as been a quad-copter control project. The project consisted of three steps. In a first step a state space model for a quad-copter had to be found. After testing the model with some simple simulations, an LQR controller based in this model was designed. Secondly a small weight disturbance …
Listen, Attend and Spell
During my Master Thesis project I re-implemented Listen, attend and Spell, an attention based speech recognition system. A key problem in speech recognition is that often it is unknown what is said when. In other words the speech signal and its transcription is unaligned. Attention based system such as the one I wrote solve this …