From Perceptrons to Transformers: The Evolution of Neural Networks in Deep Learning
From Perceptrons to Transformers: The Evolution of Neural Networks in Deep Learning
Authors:
D. Pranay Kumar1, Chetlapelly Nihal2
1Assistant Professor, Department of Computer Science and Engineering, St. Martin’s Engineering College
2UG Student, Department of Computer Science and Engineering, St. Martin’s Engineering College
Email: dpranaykumarcse@gmail.com1, chetlapellinihal@gmail.com2
Abstract:
The field of Artificial Intelligence (AI) has undergone remarkable transformation, driven largely by the evolution of neural network architectures. Beginning with simple perceptron models in the mid-20th century, neural networks have advanced into deep learning systems capable of solving highly complex tasks. This article presents a comprehensive exploration of this evolution, tracing key milestones from early linear models to modern transformer-based architectures.
It highlights how advances in computational power, large-scale data availability, and improved learning algorithms have contributed to the rapid growth of deep learning. Additionally, the article examines the integration of multimodal data, performance evaluation strategies, and current challenges such as interpretability, bias, and computational cost. The discussion emphasizes that while neural networks are revolutionizing industries, their development must align with ethical principles and responsible AI practices.