Accelerated Programme in Deep Learning and Artificial Intelligence

Jump-start your career with the Accelerated Programme in Deep Learning and Artificial Intelligence, an intensive 2-week course perfect for STEM graduates and tech professionals looking to master AI and Deep Learning's core concepts for future-ready job roles.

Course Thumbnail

Essential Skills Gained

Checkmark

Architect A.I. & Deep Learning Solutions

Checkmark

Build A.I. & Deep Learning applications

Checkmark

Interface with business users unfamiliar with technology

Checkmark

Lead A.I. & Deep Learning projects

Format

  • Instructor-led
  • 6 days with lectures and hands-on labs.

Audience

  • STEM Graduates
  • Tech Professionals
  • Data Science Enthusiasts
  • AI Researchers

Description

GET HANDS-ON WITH THE MOST DISRUPTIVE INNOVATIONS IN DATA SCIENCE, AND ENABLE YOURSELF TO SOLVE AN EVER-EVOLVING ARRAY OF ANALYTICAL PROBLEMS!

The Accelerated Programme in Deep Learning and Artificial Intelligence is an intensive 2-week program designed to help fresh graduates and experienced professionals, jump-start their career in the fastest growing AI & Deep Learning areas. Babbage Simmel, in partnership with Soothsayer Analytics, brings you this unique program that’s been designed to put you on track for the hottest job of the century in the fastest possible time. The program develops a high level of understanding quickly. This program consists of 6 in-person days of class (48 hours) spread over 2 weeks, covering basics to an in-depth understanding on Artificial Neural Networks, Shallow Learning, Back Propagation and Feed Forward Techniques to analyze images, text, and structured data. During hands-on sessions, participants will develop a functioning AI application as a final project. This will give them experience solving real AI and Deep Learning problems. Learn to:
  • Architect A.I. & Deep Learning Solutions
  • Build A.I. & Deep Learning applications
  • Interface with business users who may struggle to understand the technology
  • Recognize the limitations of A.I. & Deep Learning and avoid mistakes during production
  • Utilize best practices to ensure proper implementation and adoption
  • Demystify and visualize results for easy consumption by non-technical stakeholders
  • Lead A.I. & Deep Learning projects
  *this program is available in Columbus, OH

Calendar icon

Upcoming Course Dates

No upcoming dates. Please check back later.

Course Outline

Download PDF

Week 1: Introduction to the AI/ML

  1. Understand elements of statistical learning.

  2. Build Linear/Non-linear hypotheses.

  3. Use Loss Functions for regression and classification problems such as least squares, cross-entropy, etc.

  4. Find solutions using gradient descent.

  5. Understand issues with Bias & Variance.

  6. Understand Regularization concepts.

  7. In the lab

    1. Perform pre-processing steps on a given dataset

    2. Build a regression/classification model, with regularization

    3. Report the error metrics

Shallow Learning Fundamentals

  1. Understand Neural Networks (NN) Basics

  2. Deep dive into Perceptron concepts, and limitation

  3. Get to know about Back Propagation, and how Gradient Descent is used in Back Propagation

  4. Learn practical ways of building Shallow Networks

  5. Understand Best Practices and application on real-world problems.

  6. Learn Neural nets for word2vec representations.

  7. In the lab

    1. Work on the same dataset and achieve better accuracies

Deep Learning - Multi-Layered Perceptron

  1. Get to know issues in deepening the nets and techniques to overcome these issues.

  2. Learn Deep Learning(DL) Basics.

  3. Deep dive into Regularization, auto-encoders, RELU activation, hyper-parameter tuning and transfer learning.

  4. In the Lab:

    1. Learn to remove noise in data,

    2. use NN as feature generator for other models, or use NN as a predictor

    3. Unsupervised learning using NN. Take a high dimensional data and reduce the dimensionality, and apply clustering

Project & evaluation during Week 1 (remote work)

  1. Approx. 20 hours during Thursday, Friday and Saturday on a Project, with primary focus on

  2. Pre-Process

  3. Build a forecasting or regression model

  4. An online MCQ based test with 50 Min, 30 Questions

Week 2: Convolution Neural Net (for images)

  1. Start with Architecting a Convolution Neural Network (CNN)

  2. Learn the Geometry of CNN

  3. Understand practical aspects of building CNN

    1. Data augmentation

    2. Object Localization

  4. How to visualize a convolution net.

  5. In the Lab:

    1. Build CNN, step-by-step, with CIFAR dataset (including augmentation, ensemble)

    2. CNN for text (based on latest research paper)

Recurrent Neural Net (for Text)

  1. Learn basics of Recurrent Neural Networks (RNN)

  2. Understand architectural differences

  3. Deep dive into Long Short-Term Memory (LSTM) nets for text mining and time series

  4. Get introduced to other exciting architectures and applications (GANs)

  5. In the Lab:

    1. Build RNN for Entity Extraction

    2. Build RNN for Sentiment Classification/Analysis

Conclusion

  1. Objective of the Day:

  2. Discuss limitations of Deep Neural Networks, Architecture

  3. Learn how to scale up Deep Neural Network, and other issues

  4. Program recap

Final Project submission & evaluation (remote work)

  1. Approx. 20 hours during Thursday, Friday and Saturday on a Project, with primary focus on

    1. Image Captioning using CNN and RNN

    2. An online MCQ based test with 50 Min, 30 questions

    3. Submit final project paper the following Wednesday

Your Team has Unique Training Needs.

Your team deserves training as unique as they are.

Let us tailor the course to your needs at no extra cost.