Nex-G Innovations

PyBrain is a modular Machine Learning Library for Python. Its goal is to offer flexible, easy-to-use yet still powerful algorithms for Machine Learning Tasks and a variety of predefined environments to test and compare your algorithms. PyBrain is short for Python-Based Reinforcement Learning, Artificial Intelligence and Neural Network Library. In fact, we came up with the name first and later reverse-engineered this quite descriptive "Backronym"..

Code: NES_SK_7803

Duration: 40 Hrs /3 Weeks / Customized

Mode: Online / Offline / Onsite

+91-8826900551

• Recognize classes of optimization problems in machine learning and related disciplines.
• Learn concepts that demystify the “why” and “how” of ubiquitous topics such as regression, deep learning, and large-scale optimization, with a focus on convex and non-convex models.
• Interface with software for computing optimal solutions to a given machine learning problem.
• Understand the mathematical underpinnings of optimization methods via examples drawn from machine learning, computer vision, engineering, and data analysis.
• Understand foundational optimization ideas including gradient descent, stochastic gradient methods, higher-order methods, and more advanced optimization algorithms.
• Classify optimization problems by their tractability, difficulty, and compatibility with existing software.
• Learn to cut through the hype to make more informed choices for their own applications.

Modules Covered in the Course

• Basic notions: Modeling --- variables, criteria, constraints
• Gradient descent, stochastic gradient descent
• Intro to practicum: Modeling and optimization for least-squares
• Comparing Google Sheets to SGD in Python
• Second-order methods (Newton-type methods, quasi-Newton)
• Neural networks models
• Working with constraints in optimization
• Case study : optimal transport
• CVX and other solvers
• Sparsity, low-rank optimization, smoothness, and other considerations
• Case study : Nonlinear image analysis --- add translating to a solver
• Advanced models: GANs, adversarial optimization, robust optimization, cycle consistency
• Case study : Constructing adversarial examples
• Metric learning motivation, models, and optimization
• Classification models (NN based) with a “reject” option
• Industrial time-series case study (modeling, and optimization)
• Image sharpening: model and optimization
• Implement 2nd order trend filtering OR implement Metric Learning and try kNN
• Interaction of optimization with neural network architecture
• Case study : Clustering, embedding, and visualization
• Optimization and modeling project discussion
• Practical guide to OPTML (S+J)

Target Audience

• achelor Of Technology, Bachelor Of Engineering, Bachelor Of Science, Bachelor Of Computer Application, Master Of Technology, Master Of Engineering, Master Of Science, Master Of Computer Application.

Training Customization

• Currently Modeling And Optimization For Machine Learning has varied flavors within the industry and differing adoption strategies for learning are proliferating. To reflect this we can offer a customization service to corporate customers wishing to tailor this series of learning to deliver skills to a wide range of employee roles. Complete blended learning packagers are available that may encompass our online e-learning series, instructor-led classroom technical classes delivered for both onsite and public scheduled formats, and hands-on workshops. We have already delivered Modeling And Optimization For Machine Learning to reputed clients .