- Pertemuan 1 : Basic Neural Network [View]
- Intro to Neural Network (Basic Concept, Layer, Activation & Loss Function)
- Train Simple Neural Network using Pytorch on MNIST Dataset
- Model Evaluation (Accuracy, Precision, Recall & Confusion Matrix)
- Pertemuan 2 : Neural Network Optimization [View]
- Experiment with Neural Network (Adding Layer & Change Activation)
- Intro to Neural Network Optimizer
- Experiment with Neural Network (Change Optimizer & Learning Rate Decay)
- Intro to Dropout Layer & Training Overfitting
- Experiment Handling Overfitting using Dropout Layer
- Pertemuan 3 : Basic Convolution Neural Network (CNN) [View]
- Intro to Convolution Neural Network
- Train Simple CNN using Pytorch on MNIST Dataset
- Experiment Adding Dropout Layer to CNN
- Intro to Batch Normalization Layer
- Experiment Adding Batch Normalization Layer to CNN
- Pertemuan 4 : CNN with Attention Mechanism [View]
- Intro to Attention Mechanism
- Intro to Channel Attention : Squeeze and Excitation Block
- Intro to Spatial Attention : Self Attention & Multi-head Attention
- Experiment to recalibrate feature map using Squeeze and Excitation Block in Pytorch
- Experiment to recalibrate feature map using Self Attension in Pytorch
- Pertemuan 5 : Intro to CNN based Image Classification Model [View]
- Intro Deep Learning Image Classification Model (GoogLeNet, Resnet, ResNeXt, EfficientNet, ViT, etc.)
- Experiment with Residual Block of ResNet Model Architecture
- Intro to PyTorch Hub & ResNet-18 Pretrained Model
- Pertemuan 6 : Transfer Learning on CNN based Image Classification Model [View]
- Transfer Learning ResNet-34 using Apple2Orange Dataset
- Transfer Learning ResNet-152 using Apple2Orange Dataset
- Transfer Learning SE-ResNeXt-101 using Apple2Orange Dataset