APTx Neuron: A Unified Trainable Neuron Architecture Integrating Activation and Computation
This work addresses computational inefficiency in neural network design for machine learning practitioners, presenting a new paradigm in neuron architecture.
The paper tackles the problem of separate activation and linear transformation layers in neural networks by proposing the APTx Neuron, a unified trainable neuron that integrates both functions, achieving 96.69% test accuracy on MNIST with 332K parameters in 11 epochs.
We propose the APTx Neuron, a novel, unified neural computation unit that integrates non-linear activation and linear transformation into a single trainable expression. The APTx Neuron is derived from the APTx activation function, thereby eliminating the need for separate activation layers and making the architecture both computationally efficient and elegant. The proposed neuron follows the functional form $y = \sum_{i=1}^{n} ((α_i + \tanh(β_i x_i)) \cdot γ_i x_i) + δ$, where all parameters $α_i$, $β_i$, $γ_i$, and $δ$ are trainable. We validate our APTx Neuron-based architecture on the MNIST dataset, achieving up to $96.69\%$ test accuracy within 11 epochs using approximately 332K trainable parameters. The results highlight the superior expressiveness and computational efficiency of the APTx Neuron compared to traditional neurons, pointing toward a new paradigm in unified neuron design and the architectures built upon it. Source code is available at https://github.com/mr-ravin/aptx_neuron.