Efficient waste management is crucial for environmental sustainability and resource optimization. Traditional methods often involve manual sorting, leading to inefficiencies and increased costs. To address this challenge, an intelligent waste sorting system combines computer vision, deep learning, and hardware implementation. The project focuses on developing and integrating a neural network-based waste sorting algorithm. Using a diverse dataset, a convolutional neural network (CNN) is trained to classify various types of waste, including plastic, paper, e-waste, and organic waste. The CNN demonstrates high accuracy in identifying waste materials, even in complex real-world scenarios. The machine learning model, a ResNet, achieved a test accuracy of 93%, showcasing the effectiveness of the approach in automating and improving waste sorting processes.