×
1
  • Class and Course

    Deep Learning for the Energy Industry

    The 5-day Deep Learning for the Energy Industry training equips participants with theoretical knowledge and practical skills in implementing deep learning. Attendees learn the application of deep learning techniques to complex energy industry problems. They gain hands-on experience using AI . The course emphasizes real-world scenarios, ensuring that the students acquire the knowledge and skills to effectively use deep learning in their energy industry roles.

    1. What is Deep Learning?
      • Overview and Key Concepts
    2. Deep Learning Fundamentals
      • Neuron & Perceptron, Artificial Neural Network Basics
      • Neural Network Architecture, Fully Connected Layers
    3. Non-Linearity in Neural Networks
      • Activation Functions, Bias Node
    4. From Neuron to Neural Network
      • Perceptron, Feed Forward Neural Networks
      • Matrix Representation (Vectorization)
    5. Forward Propagation & Backpropagation
      • Basics of Forward Propagation and Backpropagation
      • Inference in Neural Networks
    1. Loss Functions
      • Understanding Objective/Loss/Cost Functions
    2. Optimization & Regularization
      • Optimizers, Learning Rate, Parameters
      • Dropout, L1 and L2 Regularization
    3. Monitoring Training
      • Overfitting & Underfitting, Strategies to Combat Them
    4. Types of Neural Networks
      • Recap: Perceptron, Feed Forward NN
      • Radial Basis NN (RBF), Deep Feed Forward (DFF)
    5. Model Training
      • Definition, Hyperparameters, Examples
    1. Deep Learning Frameworks
      • Overview, PyTorch Basics
      • DataLoaders & Datasets, Model Architecture
    2. Convolutional Neural Networks (CNN)
      • Brain's Organization, Why Convolutional Layer?
      • Convolution: Stride, Visualization of Feature Maps
    3. CNN Layers and Operations
      • Spatial Convolution, Edge Detectors, Border Effects
      • Dimension Reduction, Pooling (Max/Average)
    4. Building a CNN
      • The Whole CNN, Feature Maps to FC Layers
      • Global Average Pooling (GAP), Last FC Layer

    1. Modern CNN Architectures
      • Overview: LeNet, AlexNet, VGG, NiN, GoogLeNet, ResNet
      • Residual Connections, Batch Normalization
    2. Recurrent Neural Networks (RNN)
      • Sequence Model, Feed-forward vs Recurrent Network
      • RNN with LSTM/GRU, Gate Concept
    3. Applications of LSTM/RNN
      • Neural Machine Translation, Chat Models, Image Caption Generation
    4. Autoencoders

    1. Deep Learning for NLP
      • Introduction to NLP, Brief Research History
      • Recent Advances in NLP, GPT-3 and GPT-4 Overview
      • Multimodalities, Document AI, NLP Pipelines
    2. Vision Transformers
      • Introduction and Overview
    3. Practical Applications and Case Studies
      • Document AI - Challenges and Pipeline
      • Use Cases in Various Industries
    4. Creating Effective Prompts for GPT Models
      • Understanding Prompt Design, GPT-3 vs. GPT-4
    5. Wrap-Up and Q&A Session
      • Recap of Key Concepts, Open Discussion, and Final Queries

    Upcoming Classes

    Set a training goal, and easily track your progress

    Customize your own learning journey and track your progress when you start using a defined learning path.

    Icon
    In just few simple steps, you can customize your own learning journey in the discipline of your interest based on your immediate, intermediate and transitional goals. Once done, you can save it in NExTpert, the digital learning ecosystem, and track your progress.
    © 2024 SLB Limited. All rights reserved.