Complete Deep Learning Bootcamp with PyTorch

About this course

PyTorch Fundamentals: Tensors, computational graphs, Autograd, backpropagation, training loops, nn.

Module, loss functions, optimizers, Dataset and DataLoader.

Neural Networks: Weights, biases, forward and backward propagation, activation functions, gradient descent, optimization, weight initialization and loss functions.

Regularization & Training: L1/L2 regularization, Dropout, Batch Normalization, Layer Normalization, Instance Normalization and Early Stopping.

Convolutional Neural Networks: Convolution, kernels, feature maps, padding, stride, pooling, CNN architectures and data augmentation.

Modern CNN Architectures: VGG, ResNet, DenseNet, MobileNet and Transfer Learning.

Computer Vision: Image classification, Grad-CAM, object detection, YOLO and advanced image segmentation techniques.

Image Segmentation: U-Net, Mask R-CNN, FCN, SegNet, DeepLab, PSPNet, HRNet, BiSeNet, SegFormer and Transformer-based segmentation.

Sequence Models: RNN, LSTM, GRU, Bidirectional RNNs, BiLSTM, BiGRU, Stacked RNNs and Seq2Seq.

Attention Mechanisms: Bahdanau Attention, Luong Attention, Global & Local Attention and Self-Attention.

Transformers: QKV, Multi-Head Attention, Transformer Architecture, Encoder, Decoder, Add & Norm and Feed-Forward Networks.

Hands-On Projects: Build practical Deep Learning projects using PyTorch, real-world datasets and modern Deep Learning architectures.

Practical Learning: Learn through concepts, mathematics, implementation, coding, model training and evaluation.

Read the full description on Udemy on Udemy (opens in a new tab)

Prices, discounts and availability are set by Udemy. We may earn a commission when you purchase through links on this site.