You Ziang's Projects
Homepage for STAT 157 at UC Berkeley
🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Using BM3D to denoise
pure Python implement of BM3D
连续吸引子神经网络基本模型Basic Implementation of a Continuous-attractor Neural Network
This repository contains the Matlab code for "Extracting grid characteristics from spatially distributed place cell inputs using non-negative PCA" by Yedidyah Dordek, Daniel Soudry, Ron Meir and Dori Derdikman
DVS事件相机
:books: 极客时间电子书
Visualizations supporting HTM School
Brain-inspired multimodal hybrid neural network for robot place recognition
NeuroSLAM: A Brain inspired SLAM System for 3D Environments
Publication-ready NN-architecture schematics.
和李沐一起读论文(非官方非完善)
Perona-Malik diffusion or anisotropic diffusion is a computer vision filtering technique that aims at reducing image noise without reducing the image’s quality in the process. This diffusion technique typically resembles the process that creates a scale space, where an image generates a parameterized family of successively more and more blurred images based on a diffusion process. Each of the resulting images in this filter is given as a convolution between the image and a 2D isotropic Gaussian filter. This diffusion is a linear and space invariant transformation of the original image. Anisotropic diffusion is a much generalized version of the diffusion process. It produces a family of parameterized images where each resulting image is a combination between a filter that depends on the content of the original image and the original image itself. This means that anisotropic diffusion is a linear and space invariant transformation of the original image
Python implementation of the Perona-Malik anisotropic filter for denoising and edge detection
Self-Organizing Incremental Neural Network implementation with Python自组织增量学习神经网络SOINN
Analysis for spatially modulated spiking activity, e.g. place cells, grid cells
This package allows send differents waypoints to the navigation stack of ROS (kinetic). It can be used with the GUI interface in RVIZ or calling their services.
Rviz plugins package for showing custom info