Building Intelligent Applications with AI and ML - Level 2 Training in Switzerland

Is This The Right Course?

Who Should Attend?

• Basic familiarity with Python programming.
• Basic understanding of Data Terminologies.
• Familiarity with enterprise IT.
• Foundational knowledge in mathematical concepts like linear algebra and probability
• Basic Linux skills
• Basic SQL skills
• Should have attended 'Building Intelligent Applications with Artificial Intelligence (AI) and Machine Learning (ML) Level 1

• Understand the basics of Deep Learning
• Understand Convolutional Neural Networks, their architectures and their applications.
• Understand Recurrent Neural Networks, their architectures and their applications
• Understand the basics of Natural Language Processing.
• Understand various NLP Libraires
• Understand and perform Text Analytics
• Apply NLP techniques to predict customer sentiment
• Dealing with Real-World data

1. Deep Learning Essentials
   
   • Understanding Neural Networks, Artificial Neural Network, Perceptron concepts
   • Understanding activation functions and why they are important?
   • Understanding Convolutional Neural Networks
   • CNN Architectures
   • CNN applications
   • Understanding Recurrent Neural Networks
   • RNN Architectures
   • RNN Applications
   • Natural Language Processing
     
     • Foundations of NLP
     • Various NLP Libraries
     • Understand NLP concepts like Morphology, Lemmetization, Stemming, Part-of-Speech tagging
     • Understanding Text Analytics
     • Performing Text Analytics with a case study
   • Natural Language Processing with Deep Learning
     
     • Applications of Deep Learning in NLP
     • Deep Learning Libraries for building NLP applications
     • Word Embeddings
     • Identifying Sentiments in Customer Reviews - case study
2. Advanced NLP Models
   
   • Understand and Differentiate between LSTMs, GRUs, GPT Models
   • Understand Sequence to Sequence Models
   • Understand Attention Models
   • Understand Transformer Models
   • A Deep Dive into Machine Translation using NLP
   • Building a real-world End-End NLP Application
     
     • Data Gathering
     • Data Cleaning and Pre-processing
     • Building and evaluating NLP Models
   • GUI and REST APIs
     
     • Building UI for your Machine Learning Models
     • Building a REST API for your Models