Deep Learning Workshop
Deep learning (also known as deep structured learning, hierarchical learning or deep machine learning) is a class of machine learning algorithms. Deep learning algorithms transform their inputs through more layers than shallow learning algorithms. At each layer, the signal is transformed by a processing unit, like an artificial neuron, whose parameters are 'learned' through training.
Topics to be covered in Workshop
Module 1: Convolution Neural Networks
- Invariance, stability.
- Variability models (deformation model, stochastic model).
- Scattering networks
- Group Formalism
- Supervised Learning: classification.
- Properties of CNN representations: inevitability, stability, invariance.
- covariance/invariance: capsules and related models.
- Connections with other models: dictionary learning, LISTA.
- Other tasks: localization, regression.
- Embeddings (DrLim), inverse problems
- Extensions to non-euclidean domains
- Dynamical systems: RNNs.
Module 2: Deep Unsupervised Learning
- Autoencoders (standard, denoising, contractive, etc etc)
- Variational Autoencoders
- Adversarial Generative Networks
- Maximum Entropy Distributions
Module 3 : Miscellaneous Topics
- Non-convex optimization for deep networks
- Stochastic Optimization
- Attention and Memory Models
- Open Problems
Duration: The duration of this workshop will be two consecutive days, with eight hour session each day in a total of sixteen hours properly divided into theory and hands on sessions.
Certification Policy:
- Certificate of Participation for all the workshop participants.
- At the end of this workshop, a small competition will be organized among the participating students and winners will be awarded with a 'Certificate of Excellence'.
- Certificate of Coordination for the coordinators of the campus workshops.
Eligibility: There are no prerequisites. Anyone interested, can join this workshop.
