This repository contains numerical methods for finding solutions of a nonlinear equation as well as to approximate functions from a dataset of (x, y) points.

An implementation of multilayer perceptron(MLP) on function approximation.

A short and sweet library handling uncertainty in calculations. Can use both standard, probabilistic uncertainties and maximal uncertainties for arbitrary functions over arbitrary variables.

Dash App for visualizing function approximations by polynomials.

This project is a simple implementation of a neural network with gradient descent optimization from scratch. The goal of this project is to demonstrate how a neural network works and how the gradient descent algorithm can be used to optimize its parameters.

This project involves approximating a function to solve an optimization problem. Functions can often be costly to write in code. Approximating a function can sometimes save time and money. Especially when the code is iterated many times.

Distributed and Asynchronous Algorithm for Smooth High-dimensional Function Approximation using Orthotope B-splines

MLP network for approximating functions: implementation and experiments

Repository containing python notebooks used to teach the lab classes of the curricular unit "Numerical Methods (M2039)" at FCUP, Portugal, in study year 2023/2024

Approximating nonlinear functions with low-rank spiking networks

Seminar project at FER led by Assistant Professor Marko Čupić

Simple linear regressor that tries to approximate a simple function deployed in Tensorflow 2.0 without Keras

Function approximation using Multilayer Perceptron (MLP)

Estimation of a non-linear function using neural networks

This is a repository for Coursera Reinforcement Learning Course Notebook ,, these consist of my solutions. Feel Free to take a look , if you are stuck in Course and suggest corrections, if you find any mistake. Also Useful if you are looking for an implementation of RL-Algorithms. ** NOTE THESE NOTEBOOKS DON'T WORK AS THEY DO NOT CONTAIN UTILITY…

The focus of function approximation problems has been on identifying some suitable function without attempting to gain insight into the mechanism of the system. The performance of the model boils down to interpolation. But, in a more realistic setting, we expect test data from outside the distribution of the training set. To better extrapolate t…

Assignments and Reading Material for RL Course

This is a reposatory for implementation of different types of optimizers (SGD, RMSprop, Adam etc.) with three different use cases Function Approximation, Multi-class Single-label Classification and Multi-class Multi-label Classification)