Curriculum

  • 6 Sections
  • 42 Lessons
  • 20 Weeks
Expand all sectionsCollapse all sections
  • Introduction to Python
    0
    • Introduction to Logistic Regression
      0
      • Introduction to Artificial Neural Network
        11
        • 3.1
          History of Neural networks and Deep Learning.
        • 3.2
          How Biological Neurons work?
        • 3.3
          Growth of biological neural networks.
        • 3.4
          Diagrammatic representation: Logistic Regression and Perceptron.
        • 3.5
          Multi-Layered Perceptron (MLP).
        • 3.6
          Notation.
        • 3.7
          Training a single-neuron model.
        • 3.8
          Backpropagation.
        • 3.9
          Activation functions.
        • 3.10
          Vanishing Gradient problem.
        • 3.11
          Bias-Variance tradeoff.
      • Deep Multi-layer perceptrons
        11
        • 4.1
          Deep Multi-layer perceptrons:1980s to 2010s
        • 4.2
          Dropout layers & Regularization.
        • 4.3
          Rectified Linear Units (ReLU).
        • 4.4
          Weight initialization.
        • 4.5
          Batch Normalization.
        • 4.6
          Optimizers:Hill descent in 3D and contours.
        • 4.7
          Adam
        • 4.8
          Which algorithm to choose when?
        • 4.9
          Gradient Checking and clipping
        • 4.10
          Softmax and Cross-entropy for multi-class classification.
        • 4.11
          How to train a Deep MLP?
      • Convolutional Neural Network
        13
        • 5.1
          Biological inspiration: Visual Cortex
        • 5.2
          Convolution:Edge Detection on images.
        • 5.3
          Convolution:Padding and strides
        • 5.4
          Convolution over RGB images.
        • 5.5
          Convolutional layer.
        • 5.6
          Max-pooling.
        • 5.7
          CNN Training: Optimization
        • 5.8
          Receptive Fields and Effective Receptive Fields
        • 5.9
          ImageNet dataset.
        • 5.10
          Data Augmentation.
        • 5.11
          Convolution Layers in Keras
        • 5.12
          AlexNet
        • 5.13
          VGGNet
      • Recurrent Neural Network
        7
        • 6.1
          Why RNNs?
        • 6.2
          Recurrent Neural Network
        • 6.3
          Training RNNs: Backprop
        • 6.4
          Types of RNNs
        • 6.5
          Need for LSTM/GRU
        • 6.6
          LSTM
        • 6.7
          GRUs

      Deep Learning & AI

      This content is protected, please login and enroll in the course to view this content!
      Next How Biological Neurons work? Next