Diving into Transformer : Attention Is All You Need!Transformer is a deep neural network architecture that introduced in “attention is all you need”. It is designed for sequence to sequence tasks. Particularly, excelling in natural language processing (NLP). It eliminates RNN and CNN in favor of self ...Mar 10, 2025 · 6 min readelrizanda.hashnode.dev
Intel Scene Image Classification VGG Hyperparameter TuningOverview Hyperparameter tuning is one of the lifecycle of designing and building machine learning algorithm. Hyperparameter tuning is a process to find the best parameter for algorithm based in our case. Although may not significantly improve the per...Mar 10, 2025 · 5 min readelrizanda.hashnode.dev
Regularization Techniques to Improve Deep Learning PerformanceOverview When building and training deep learning models we often facing the problem of overfitting. Overfitting may happen due the model complexity or the model is “memorized” the training dataset instead of learning generalizable patterns. This be...Dec 27, 2024 · 5 min readelrizanda.hashnode.dev
Learning to Build ResNet for Intel Scene Classification from ScratchOverview This dataset is scene classification dataset that published by Intel. This dataset also used in previous implementation. Dataset consist of 6 class that consist of difference categories like buildings, forest, glacier, mountain, sea, and str...Dec 24, 2024 · 8 min readelrizanda.hashnode.dev
MobileNet Explained: A Slim and Efficient CNN ModelOverview The paper “MobileNet: Efficient Convolutional Neural Network for Mobile Vision Application” authored by Andrew G. Howard, Menglong Zhu, and others in 2017, introduces a new approach for convolutional neural network which is more efficient an...Dec 24, 2024 · 3 min readelrizanda.hashnode.dev
