I started this course with thought of resolving problem from work. The idea was not so simple: recognition and outlining using vector lines aeronautical objects at the airports on satelite maps. This task was hard, because airports are not the same in every region – let’s compare for example Frankfurt and Dubai airport: As itWięcej oMachine Learning – Summer School of AI on Technical University of GDN[…]
What is a Perceptron? A Perceptron is an algorithm used for supervised learning of binary classifiers. Binary classifiers decide whether an input, usually represented by a series of vectors, belongs to a specific class. In short, a perceptron is a single-layer neural network. They consist of four main parts including input values, weights and bias, net sum, and an activation function.Więcej oMachine Learning – perceptron[…]
Super easy explanation of this topic is on this Polish blog: https://ichi.pro/pl/zrozumienie-matematyki-stojacej-za-gradient-descent-243979318452334 Strongly recommend!
I am participating as reviewer of this Masacchuset Inistitut of Technology course. I always admired this university as one of the best in the world. For me it was always unrecheable to study in USA, but thanks to coronovirus time, I discovered that they lead free courses on different topics. As my recent interest isWięcej oMIT – Machine Learning with Python-From Linear Models to Deep Learning[…]
How to achieve this in pytohn: import pandas as pd import numpy as np from sklearn.tree import DecisionTreeClassifier from sklearn.model_selection import cross_val_score import xgboost as xgb import eli5 from collections import Counter import gc Firstly we import libraries: pandas, numpy-for data analysis and preparation. From library sklearn we import AI model and needed operations onWięcej oMachine Learning – introduction[…]
Here are another two interesting www sites for learning AI and DataScience: This site consists of free DataScience courses and datasets: https://www.kaggle.com/ 2. This is free course of AI in German: https://bootcamp.codecentric.ai/
Recently I also found this very interesting page for visualisation of different datasets: http://networkrepository.com/index.php
Recently I participated in very interesting workshop on Technical University in GDN. Workshop was lead by Tomasz Kocejko from faculty: Medical Telematics. This workshop presented possibilites of using Machine Learning models on mobile devices. More info: https://aibay.ai/wp-content/uploads/2020/11/kursy_Inferencja_Android_DIH.pdf This is only an example what could be achieved with Transfer Learning. The goal is: creation of mobileWięcej oAI – cats and dogs classifier[…]