AkshayS21

Reinforcement-Learning-for-Optimal-Financial-Trading

Implementation of the DDPG algorithm for Optimal Finance Trading

Toronto-Neighbourhoods-Clustering

Location based clustering of Toronto Neighborhoods

Reacher-Environment-Continuous-Control-with-DDPG-algorithm

Implementation of the DDPG algorithm to solve Continuous Control Reacher Environment

Soccer-Environment-Multi-Agent-RL

Training a Multi-Agent DDPG Algorithm to play Soccer

Coursera_Capstone

Data Science Capstone project using Location Data

Navigation-Project-with-DQN

Using the Deep Q-Learning Network to train an Agent for Navigation

Attention-Mechanism

Attention Model for translating dates of various formats to machine readable format

Best-Classifier-Model

Determine the best classification algorithm to classify a Loan data

Chicago-Crime-data-analysis

Using SQL to analyse Chicago Crime data

Collaborate-and-Compete-Tennis-Project

Implementation of the MultiAgent Reinforcement Learning Algorithm

Exploratory-Data-Analysis

Exploratory Data Analysis of a Car Dataset to predict its price

Neural-Style-Transfer

Implementation of the Neural Style Transfer (NST) algorithm

Word-Vector-Operations

Word Analogy and Debiasing

Word-Vectors-to-Emotion

Convert sentences to emotions (e.g. Emojis or Rating stars or rotten tomatoes).

Convolutional-Neural-Network-with-Tensorflow

Usig Tensorflow to apply convolutional neural network

Deep-Reinforced-Learning-Projects

Deep Reinforced Learning Projects

deep-reinforcement-learning

Repo for the Deep Reinforcement Learning Nanodegree program

Github-Course

My project

Hello_world

Introduction

Image-classification-using-Keras

Just basic model building using Keras library

Implementation-of-the-ResNet50-model

Implementation-of-the-YOLO-model

Implementation of the YOLO model to Autonomous driving Car detection

pandas_data_analysis

Analysis of some data using Pandas

Python_Advanced

Advanced Python notebooks

Test-Groups-Optimization

Automating the repetitive and tedious task of dividing test groups into two most optimal segments as part of the A/B testing process.