Introduction: History of Neural network, an overview of Linear models, Hebbian learning Processing units: Perceptrons (classification), Limitations of Linear nets and Perceptrons, Activation functions, Error functions.
Neural Network : Neural network architecture, Multi-layer neural network, Practical advice, Optimization, Bias-variance dilemma, Overfitting, Inductive bias,
Training Neural Network: Risk minimization, loss function, back propagation, regularization, model selection, and Optimization.
Conditional Random Fields: Linear chain, partition function, Markov network, belief propagation, Training CRFs, Hidden Markov Model, Entropy.
Deep Learning: Deep Feed Forward network, regularizations, training deep models, dropouts, Convolutional Neural Network, Recurrent Neural Network, Deep Belief Network.
Probabilistic Neural Network: Hopfield Net, Boltzman machine, RBMs, Sigmoid net, Autoencoders.
Deep Learning research: Object recognition, sparse coding, computer vision, natural language processing.
Deep Learning Tools: Caffe, Tlieano, Torch.
- Teacher: Kamal Kant
- Teacher: Ram Nayan Mishra