GitHub

11_01_softmax_cross_entropy.py

return np.exp(x) / np.sum(np.exp(x), axis=0) Y_pred_good = torch.tensor([[0.1, 1.0, 2.1], [2.0, 1.0, 0.1], [0.1, 3.0, 0.1]]) Y_pred_bad = torch.tensor([[2.1, 1.0, 0.1 ...
GitHub

ocdbytes-ai/Softmax-regression

A from-scratch implementation of softmax regression (multinomial logistic regression) in PyTorch, trained on the Fashion-MNIST dataset. No nn.Module or built-in loss functions — everything is ...
IEEE

A Softmax-Free Loss Function Based on Predefined Optimal-Distribution of Latent Features for Deep Learning Classifier

Abstract: In the field of pattern classification, the training of deep learning classifiers is mostly end-to-end learning, and the loss function is the constraint on the final output (posterior ...
IEEE

SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference

Abstract: Transformers have shown remarkable performance in both natural language processing (NLP) and computer vision (CV) tasks. However, their real-time inference speed and efficiency are limited ...