This project focuses on the classification of Electroencephalogram (EEG) signals for the early detection of Autism Spectrum Disorder (ASD) using a diverse set of machine learning and deep learning models. The machine learning models, including Logistic Regression, Support Vector Classifier, K-Nearest Neighbors, Decision Tree, Random Forest, XGBoost, and Gaussian Naive Bayes, leverage carefully selected statistical features extracted from EEG signals. Deep learning models, a Convolutional Neural Network (CNN), and a CNN-Recurrent Neural Network (CNN-RNN) hybrid named ChronoNet, operate directly on temporal features derived from EEG epochs. The study aims to compare the efficacy of these models in unraveling subtle neural patterns indicative of ASD. Through rigorous training, evaluation, and interpretability analysis, this research contributes to the advancement of early diagnosis methods, holding potential implications for improving outcomes and interventions in individuals with neurodevelopmental disorders.