Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Foundations of Machine Learning and Recurrent Neural Networks (RNN)
- Neural Networks (NN) and RNNs
- Backpropagation
- Long Short-Term Memory (LSTM)
TensorFundamentals
- Creating, initializing, saving, and restoring TensorFlow variables
- Feeding, reading, and preloading data into TensorFlow
- Leveraging TensorFlow infrastructure for large-scale model training
- Visualizing and assessing models using TensorBoard
TensorFlow Mechanics 101
- Tutorial Resources
- Data Preparation
- Download Procedures
- Inputs and Placeholders
- Graph Construction
- Inference
- Loss Calculation
- Training
- Model Training
- The Graph
- The Session
- Training Loop
- Model Evaluation
- Constructing the Evaluation Graph
- Evaluation Outputs
Advanced Techniques
- Threading and Queues
- Distributed TensorFlow
- Documentation and Model Sharing
- Custom Data Readers
- Utilizing GPUs¹
- Managing TensorFlow Model Files
TensorFlow Serving
- Introduction
- Basic Serving Tutorial
- Advanced Serving Tutorial
- Inception Model Serving Tutorial
Convolutional Neural Networks
- Overview
- Objectives
- Tutorial Highlights
- Model Architecture
- Code Organization
- CIFAR-10 Model
- Model Inputs
- Model Predictions
- Model Training
- Launching and Training the Model
- Model Evaluation
- Multi-GPU Model Training¹
- Device Placement for Variables and Operations
- Launching and Training on Multiple GPU Cards
Deep Learning for MNIST
- Setup
- Loading MNIST Data
- Starting the TensorFlow InteractiveSession
- Building a Softmax Regression Model
- Placeholders
- Variables
- Predicted Class and Cost Function
- Model Training
- Model Evaluation
- Constructing a Multilayer Convolutional Network
- Weight Initialization
- Convolution and Pooling
- First Convolutional Layer
- Second Convolutional Layer
- Fully Connected Layer
- Output Layer
- Training and Evaluating the Model
Image Recognition
- Inception-v3
- C++
- Java
¹ Topics involving GPU usage are not included in remote courses. They may be offered in classroom-based sessions, subject to prior agreement, and only if both the instructor and all participants possess laptops equipped with supported NVIDIA GPUs running 64-bit Linux (provided by participants, not NobleProg). NobleProg cannot guarantee the availability of instructors with the necessary hardware.
Requirements
- Python
28 Hours
Testimonials (1)
Very updated approach or CPI (tensor flow, era, learn) to do machine learning.
