Name: Mateusz Ochal
Type: User
Company: University of Edinburgh, Heriot-Watt University
Bio: Few Shot Learning; Meta Learning; Underwater Vision; PhD Candidate at Edinburgh Centre for Robotics
Location: UK
Blog: mattochal.github.io
Mateusz Ochal's Projects
Extended Project
This repository contains instructions and explanation of how to hook up a servo to an AVR micro controller (AT90USB1286)
Computing Project
Code for: "Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes" and "TaskNorm: Rethinking Batch Normalization for Meta-Learning"
My third year project implementing the LOLA algorithm, myLOLA contains the update rules
A demo for real-time task-by-task analysis of FSL algorithms.
Meta Learning for Semi-Supervised Few-Shot Classification
C# google maps api interface for interacting with the backend web services for Google Maps
PyTorch implementation for "Few-Shot Learning with Class Imbalance"
Servo controlled light switch
Website infrastructure for openmirage.org
Motion sensor light with wireless phone connection for lazy people who don't want to get up to turn the light on
2 Player Arduino Reaction Game with LEDs and switches
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Session Plan For Robosoc 2017
Scaled-YOLOv4: Scaling Cross Stage Partial Network
Thales Competition
Shape recognition with machine learning and tools for efficient image dataset gathering
adding
adding
A deep Q learning demonstration using Google Tensorflow
C# wrapper around excellent wkhtmltopdf console utility.
This is a my coursework I did for my Computer Science course at the University of Southampton.