Pinned Repositories
Adaptive-LMS-Filtering
This repository also includes a matlab version of the lms algorithm (more comments) and a version of delta learning using the bipolar sigmoid function.
Bosch-BNO055-NMAM-interrupt
Library to support no- and any motion interrupt on the BNO055 9 DoF sensor by Bosch
BPTT-Lipschitzness
Train mismatch-robust SNNs using BPTT and local Lipschitzness
CapsuleNetwork
Capsule Network implementation in TensorFlow 2.0
chaze-esp32
Hardware code for the Chaze power paddle for swimmers
Convolutional-LadderNet
Tensorflow implementation of the Ladder Network with convolutional Layers. The Ladder Network consists of an Encoder and Decoder with lateral skip connections that jointly optimize a supervised and unsupervised cost function, thus making it extremely suitable for semi-supervised learning. This repository can be further extended by adding for example recurrent layers. See more information about the Ladder Network here: https://arxiv.org/abs/1507.02672
Information-Theory-in-Deep-Learning
This is a tensorflow implementation, aiming at using the Mutual Neural Estimator proposed in (MINE, Belghazi et al) to reconstruct the images of Tishby and Zariv's paper, which can be found here: https://arxiv.org/abs/1703.00810 . Please be aware that the argument of 'compression' in the layers as a cause of extracting features is a little misleading since the mutual information is invariant under nonlinear transformations as described here: https://arxiv.org/abs/1810.05728 which was recently published.
On-Chip-EBN-Learning
Software simulations and circuit schematics for the paper "Efficient Balanced Networks as Integrated Circuits"
Semi-supervised-learning-using-ladder-networks
Semi-Supervised multi-class classification, Task 4 ETH Zürich, Intro ML
SPAA
Spiking Probabilistic Adversarial Attack
jubueche's Repositories
jubueche/Convolutional-LadderNet
Tensorflow implementation of the Ladder Network with convolutional Layers. The Ladder Network consists of an Encoder and Decoder with lateral skip connections that jointly optimize a supervised and unsupervised cost function, thus making it extremely suitable for semi-supervised learning. This repository can be further extended by adding for example recurrent layers. See more information about the Ladder Network here: https://arxiv.org/abs/1507.02672
jubueche/Information-Theory-in-Deep-Learning
This is a tensorflow implementation, aiming at using the Mutual Neural Estimator proposed in (MINE, Belghazi et al) to reconstruct the images of Tishby and Zariv's paper, which can be found here: https://arxiv.org/abs/1703.00810 . Please be aware that the argument of 'compression' in the layers as a cause of extracting features is a little misleading since the mutual information is invariant under nonlinear transformations as described here: https://arxiv.org/abs/1810.05728 which was recently published.
jubueche/chaze-esp32
Hardware code for the Chaze power paddle for swimmers
jubueche/Adaptive-LMS-Filtering
This repository also includes a matlab version of the lms algorithm (more comments) and a version of delta learning using the bipolar sigmoid function.
jubueche/SPAA
Spiking Probabilistic Adversarial Attack
jubueche/Bosch-BNO055-NMAM-interrupt
Library to support no- and any motion interrupt on the BNO055 9 DoF sensor by Bosch
jubueche/BPTT-Lipschitzness
Train mismatch-robust SNNs using BPTT and local Lipschitzness
jubueche/CapsuleNetwork
Capsule Network implementation in TensorFlow 2.0
jubueche/On-Chip-EBN-Learning
Software simulations and circuit schematics for the paper "Efficient Balanced Networks as Integrated Circuits"
jubueche/Resnet32-ICLR
jubueche/RSE
ETHZ Rigorous Software Engineering
jubueche/chaze-azure-function
Function triggered by blob-upload, responsible for decompression and SQL DB entry
jubueche/accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
jubueche/analog-moe
Analog Mixture of Experts layer implemented in Triton
jubueche/arduino-esp32
Arduino core for the ESP32
jubueche/azure-iot-sdk-c
A C99 SDK for connecting devices to Microsoft Azure IoT services
jubueche/chaze-tile
jubueche/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
jubueche/DM-network-rockpool
jubueche/eDetect
eDetect: A fast Error Detection and Correction Tool for Live Cell Imaging Data Analysis
jubueche/esp-azure
SDK to connect ESP8266 and ESP32 to Microsoft Azure IoT services
jubueche/iSTDP
Implementation of STDP-like learning rule for inh. synapses leading to tight balance respecting Dale's law (see Vogels et al 2011, Science)
jubueche/jubueche.github.io
jubueche/Learning-In-Deep-ANN-and-BNN
jubueche/OptimalWeights
jubueche/pytorch_resnet_cifar10
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.
jubueche/Rockpool
jubueche/RV-3028_C7-Arduino_Library
An Arduino library for the extremely low power, very precise, and highly configurable RV-3028-C7 Real Time Clock from Micro Crystal.
jubueche/SSRN
This is a tensorflow and keras based implementation of SSRNs in the TGRS paper "Spectral-Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework".
jubueche/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.