Deep Learning - Course Details
Master Deep Learning with neural networks. Learn CNNs, RNNs, transformers, and modern architectures. Apply deep learning to real-world problems.
- 4.5 Rating
What you'll learn?
- Neural network fundamentals
- Convolutional Neural Networks
- Recurrent Neural Networks
- Transfer learning
- Training and optimization
Requirements
- Machine Learning basics
- Python and NumPy
- Understand fundamentals of Deep Learning
- Perceptron and multilayer networks
- Layers, neurons, weights, and biases
- Sigmoid, Tanh, ReLU, Leaky ReLU, Softmax
- Mean Squared Error (MSE)
- Cross-Entropy Loss
- Hinge Loss
- Forward propagation
- Backward propagation
- Gradient descent and weight updates
- CNN concepts and architecture
- Convolution, pooling, and fully connected layers
- Predefined CNN models for image classification
- Modern CNN architectures: ResNet, DenseNet, MobileNet, VGGNet, Inception v3
- RNN concepts and architecture
- Sequence modeling and time series
- LSTM and GRU for text modeling
- Hyperparameter tuning
- Regularization techniques (Dropout, L2/L1)
- Learning rate scheduling
- CNN image classifier using predefined and modern architectures
- RNN-based text prediction, sentiment analysis, or sequence modeling
- Final end-to-end Deep Learning project
Document
No FAQ items for this course yet.
No videos for this course yet.
