Deep Learning Course

Build practical Deep Learning skills with neural networks, CNNs, RNNs, LSTMs, transformers, PyTorch, TensorFlow, computer vision, NLP, deployment, and MLOps. Learn through guided labs, projects, evaluations, and portfolio development.

- AI, ML, and Deep Learning concepts

- Neural network terminology

- Tensors, vectors, and matrices

- Training, validation, and test data

- Loss functions and metrics

- Python workflows for Deep Learning

- NumPy arrays and tensor operations

- Data loading and preprocessing

- Feature scaling and normalization

- Dataset splitting and batching

- Perceptrons and multilayer networks

- Activation functions

- Forward propagation

- Backpropagation intuition

- Gradient descent and optimizers

- TensorFlow ecosystem

- Keras model building

- Sequential and functional APIs

- Training callbacks

- Model saving and loading

- Tensors and autograd

- PyTorch datasets and dataloaders

- Building training loops

- Optimizers and schedulers

- Debugging model training

- Convolution and pooling

- Image classification

- Data augmentation

- Transfer learning

- CNN evaluation and error analysis

- Sequential data concepts

- Recurrent neural networks

- LSTM and GRU networks

- Time-series and text sequences

- Sequence model evaluation

- Attention mechanisms

- Transformer architecture

- Tokenization and embeddings

- NLP classification tasks

- Pretrained model usage

- Model serving basics

- APIs and inference pipelines

- Monitoring model performance

- Versioning and reproducibility

- Deployment best practices

- End-to-end Deep Learning project

- Problem framing and dataset selection

- Training and evaluation report

- Deployment demo

- Portfolio documentation and interview preparation