Description
Deep Learning and Applications with Python Training is a 3-day live online or in-person program for participants with basic Python and machine learning knowledge. The curriculum runs from the fundamentals of artificial neural networks to CNNs, object detection, and RNN/LSTM, and covers deep learning applications in Python.
Deep learning focuses on learning patterns in data with multi-layer artificial neural networks. The program covers mathematical foundations, model training, performance measurement, and the classification, image analysis, and prediction examples in the current curriculum.
Outline
Overview of Deep Learning
What Is Deep Learning?
Artificial Intelligence, Machine Learning, and Deep Learning
Real-Life Examples
Why Deep Learning
Recent Developments in Deep Learning
Foundations of Deep Learning
Artificial Neural Networks (ANN)
Understanding Deep Learning
Basic Concepts of Deep Learning
- Mathematical Foundations
- Activation Functions
- Gradient Descent Algorithms
- Loss Functions
- Backpropagation Algorithm
- Tensor Operations
- Time Series Data
- Text Data
- Images
- Videos
- Evaluation Metrics for Deep Learning
- Confusion Matrix
- Accuracy, Recall, Precision, AP, mAP
Tools and Setup for the Deep Learning Development Environment
Data Labeling Tools
Python Development Environment
- Anaconda – Jupyter Notebook
- Google Colab
Python-Based DNN Frameworks
- Keras
- TensorFlow
- PyTorch
Setting Up the Deep Learning Application Environment with Python and First Application
- Defining and Training a Deep Network
- Loading the Dataset and Preparing It for the Network Structure
- Network Models
- Sequential API
- Functional API
- Defining Network Layers
- Compiling and Optimizing the Network
- Measuring the Performance of the Trained Network
- Training and Testing Processes
- Saving the Trained Network and Weights
Basic Application Examples
- Binary Classification Example (IMDB Movie Reviews)
- Multiclass Classification Example (News Classification – Reuters)
Convolutional Neural Networks (CNN)
Convolutional Neural Networks
Layers of Convolutional Neural Networks
- Convolution Layer
- Batch Normalization and Activation Layer
- Pooling Layer
- Fully Connected Layer
- Dropout
CNN Models
CNN Application Examples
- Sample Application: Waste Classification
- Sample Application: Facial Expression Analysis
- Sample Application: Text Data Processing (IMDB Reviews)
DNN-Based Object Detection Models
- Two-Stage Detectors
- Single-Stage Detectors
- You Only Look Once – YOLO
- Sample Application: Vehicle Recognition with YOLO
Recurrent Neural Networks (RNN)
- Recurrent Neural Networks
- Long Short-Term Memory Networks (LSTM)
- Prediction Application with LSTM (Energy Consumption, Temperature, etc.)
Prerequisites
A basic knowledge of Python and machine learning.
Related Training and Quote
To deepen the focus on object recognition, see the Object Recognition from Images with YOLO Training; for a broader data processing scope, see the Big Data and Applications with Python Training programs.
To get a training plan and price quote for your organization, you can fill out the Contact Form on this page. For other ways to reach us, you can use the BlueMark Academy contact page.
Frequently Asked Questions
How Long Is the Deep Learning with Python Training?
The training lasts 3 days.
Is the Training Offered Online?
The training format on the page is live online or in person.
Are There Any Prerequisites?
Participants need a basic knowledge of Python and machine learning.
Which Deep Learning Tools Are Covered?
The program covers Keras, TensorFlow, and PyTorch, with Anaconda, Jupyter Notebook, and Google Colab as working environments.
Are CNN, YOLO, and LSTM Topics Covered?
Yes. The curriculum includes CNN models, DNN-based object detection, vehicle recognition with YOLO, and a prediction application with LSTM.
How Can I Request a Quote for Corporate Training?
You can submit your organization’s training needs through the Contact Form on this page and request a training plan and price quote.