Introduction to Pre-trained Models Training Course
Pre-trained models are a cornerstone of modern artificial intelligence, offering ready-made capabilities that can be adapted for a wide range of applications. This course introduces participants to the fundamentals of pre-trained models, their architecture, and their practical use cases. Participants will learn how to leverage these models for tasks such as text classification, image recognition, and more.
This instructor-led, live training (delivered either online or on-site) is designed for beginner-level professionals who wish to understand the concept of pre-trained models and learn how to apply them to solve real-world problems without building models from scratch.
By the end of this training, participants will be able to:
- Understand the concept and benefits of pre-trained models.
- Explore various pre-trained model architectures and their use cases.
- Fine-tune a pre-trained model for specific tasks.
- Implement pre-trained models in simple machine learning projects.
Course Format
- Interactive lectures and discussions.
- Abundant exercises and practical practice.
- Hands-on implementation in a live-lab environment.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
Course Outline
Introduction to Pre-trained Models
- What are pre-trained models?
- Benefits of using pre-trained models
- Overview of popular pre-trained models (e.g., BERT, ResNet)
Understanding Pre-trained Model Architectures
- Model architecture fundamentals
- Transfer learning and fine-tuning concepts
- How pre-trained models are built and trained
Setting Up the Environment
- Installing and configuring Python and relevant libraries
- Exploring pre-trained model repositories (e.g., Hugging Face)
- Loading and testing pre-trained models
Hands-On with Pre-trained Models
- Using pre-trained models for text classification
- Applying pre-trained models to image recognition tasks
- Fine-tuning pre-trained models for custom datasets
Deploying Pre-trained Models
- Exporting and saving fine-tuned models
- Integrating models into applications
- Basics of deploying models in production
Challenges and Best Practices
- Understanding model limitations
- Avoiding overfitting during fine-tuning
- Ensuring ethical use of AI models
Future Trends in Pre-trained Models
- Emerging architectures and their applications
- Advances in transfer learning
- Exploring large language models and multimodal models
Summary and Next Steps
Requirements
- Basic understanding of machine learning concepts
- Familiarity with Python programming
- Basic knowledge of data handling using libraries such as Pandas
Audience
- Data scientists
- AI enthusiasts
Open Training Courses require 5+ participants.
Introduction to Pre-trained Models Training Course - Booking
Introduction to Pre-trained Models Training Course - Enquiry
Provisional Upcoming Courses (Require 5+ participants)
Related Courses
AdaBoost Python for Machine Learning
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is designed for data scientists and software engineers who wish to use AdaBoost to develop boosting algorithms for machine learning with Python.
By the end of this training, participants will be able to:
- Set up the necessary development environment to begin building machine learning models with AdaBoost.
- Understand the ensemble learning approach and how to implement adaptive boosting.
- Learn how to build AdaBoost models to enhance machine learning algorithms in Python.
- Apply hyperparameter tuning to improve the accuracy and performance of AdaBoost models.
AlphaFold: AI-Driven Protein Structure Prediction and Interpretation
7 HoursThis instructor-led, live training in New Zealand (online or onsite) is aimed at biologists who wish to understand how AlphaFold works and use AlphaFold models as guides in their experimental studies.
By the end of this training, participants will be able to:
- Understand the basic principles of AlphaFold.
- Learn how AlphaFold works.
- Learn how to interpret AlphaFold predictions and results.
Anaconda Ecosystem for Data Scientists
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is aimed at data scientists who wish to leverage the Anaconda ecosystem to capture, manage, and deploy packages and data analysis workflows within a single platform.
By the end of this training, participants will be able to:
- Install and configure Anaconda components and libraries.
- Understand the core concepts, features, and benefits of Anaconda.
- Manage packages, environments, and channels using Anaconda Navigator.
- Use Conda, R, and Python packages for data science and machine learning.
- Explore practical use cases and techniques for managing multiple data environments.
Creating Custom Chatbots with Google AutoML
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is aimed at participants with varying levels of expertise who wish to leverage Google's AutoML platform to build customised chatbots for various applications.
By the end of this training, participants will be able to:
- Understand the fundamentals of chatbot development.
- Navigate the Google Cloud Platform and access AutoML.
- Prepare data for training chatbot models.
- Train and evaluate custom chatbot models using AutoML.
- Deploy and integrate chatbots into various platforms and channels.
- Monitor and optimise chatbot performance over time.
Pattern Recognition
21 HoursThis instructor-led, live training in New Zealand (online or onsite) introduces participants to the field of pattern recognition and machine learning. It explores practical applications across statistics, computer science, signal processing, computer vision, data mining, and bioinformatics.
By the end of this training, participants will be able to:
- Apply core statistical methods to pattern recognition.
- Use key models such as neural networks and kernel methods for data analysis.
- Implement advanced techniques to tackle complex problem-solving challenges.
- Improve prediction accuracy by combining different models.
DataRobot
7 HoursThis instructor-led, live training in New Zealand (online or onsite) is aimed at data scientists and data analysts who wish to automate, evaluate and manage predictive models using DataRobot's machine learning capabilities.
By the end of this training, participants will be able to:
- Load datasets into DataRobot to analyse, assess and perform quality checks on data.
- Build and train models to identify key variables and meet prediction targets.
- Interpret models to generate valuable insights that support business decision-making.
- Monitor and manage models to maintain optimised prediction performance.
Edge AI with TensorFlow Lite
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is aimed at intermediate-level developers, data scientists, and AI practitioners who wish to leverage TensorFlow Lite for Edge AI applications.
By the end of this training, participants will be able to:
- Understand the fundamentals of TensorFlow Lite and its role in Edge AI.
- Develop and optimise AI models using TensorFlow Lite.
- Deploy TensorFlow Lite models on various edge devices.
- Use tools and techniques for model conversion and optimisation.
- Implement practical Edge AI applications using TensorFlow Lite.
Google Cloud AutoML
7 HoursThis instructor-led, live training in New Zealand (online or on-site) is designed for data scientists, data analysts, and developers who wish to explore AutoML products and features to create and deploy custom ML training models with minimal effort.
By the end of this training, participants will be able to:
- Explore the AutoML product line to implement various services for different data types.
- Prepare and label datasets to build custom ML models.
- Train and manage models to produce accurate and fair machine learning outcomes.
- Make predictions using trained models to meet business objectives and needs.
Kaggle
14 HoursThis instructor-led, live training in New Zealand (available online or on-site) is tailored for data scientists and developers who aspire to learn and advance their careers in data science using Kaggle.
By the end of this training, participants will be able to:
- Gain a solid understanding of data science and machine learning.
- Explore the fundamentals of data analytics.
- Learn how Kaggle operates and leverage its features effectively.
Kubeflow Essentials: Build, Train & Serve with Kubernetes
14 HoursKubeflow is an open-source platform designed to streamline building, training, and deploying machine learning workloads on Kubernetes.
This instructor-led, live training (online or onsite) is aimed at beginner-level to intermediate-level professionals who wish to build reliable ML workflows using Kubeflow.
Upon completion of this training, attendees will gain the skills to:
- Navigate the Kubeflow ecosystem and core components.
- Build reproducible workflows with Kubeflow Pipelines.
- Run scalable training jobs on Kubernetes.
- Serve machine learning models efficiently using Kubeflow Serving.
Course Format
- Guided presentations and collaborative discussions.
- Hands-on labs using real Kubeflow components.
- Practical exercises to build end-to-end ML workflows.
Course Customisation Options
- Customised versions of this training can be arranged to align with your team’s technology stack and project requirements.
Kubeflow Fundamentals
28 HoursThis instructor-led, live training in New Zealand (online or on-site) is aimed at developers and data scientists who wish to build, deploy, and manage machine learning workflows on Kubernetes.
By the end of this training, participants will be able to:
- Install and configure Kubeflow both on-premises and in the cloud.
- Build, deploy, and manage ML workflows using Docker containers and Kubernetes.
- Execute complete machine learning pipelines across diverse architectures and cloud environments.
- Use Kubeflow to launch and manage Jupyter notebooks.
- Construct ML training, hyperparameter tuning, and serving workloads across multiple platforms.
Machine Learning for Mobile Apps using Google’s ML Kit
14 HoursThis instructor-led, live training (online or onsite) is aimed at developers who wish to use Google’s ML Kit to build machine learning models that are optimised for processing on mobile devices.
By the end of this training, participants will be able to:
- Set up the necessary development environment to start developing machine learning features for mobile apps.
- Integrate new machine learning technologies into Android and iOS apps using the ML Kit APIs.
- Enhance and optimise existing apps using the ML Kit SDK for on-device processing and deployment.
Machine Learning with Random Forest
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is designed for data scientists and software engineers who wish to harness Random Forest to build machine learning models for large-scale datasets.
By the end of this training, participants will be able to:
- Set up the required development environment to begin building machine learning models using Random Forest.
- Understand the benefits of Random Forest and how to apply it to solve classification and regression problems.
- Learn how to manage large datasets and interpret the output of multiple decision trees within the Random Forest framework.
- Evaluate and optimise machine learning model performance through hyperparameter tuning.
Advanced Analytics with RapidMiner
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is designed for intermediate-level data analysts who want to learn how to use RapidMiner to estimate and forecast values, and to leverage analytical tools for time series forecasting.
By the end of this training, participants will be able to:
- Apply the CRISP-DM methodology, select appropriate machine learning algorithms, and improve model construction and performance.
- Use RapidMiner to estimate and forecast values, and utilise analytical tools for time series forecasting.
GPU Data Science with NVIDIA RAPIDS
14 HoursThis instructor-led, live training in New Zealand (available online or on-site) is intended for data scientists and developers who wish to use RAPIDS to build GPU-accelerated data pipelines, workflows, and visualisations, applying machine learning algorithms such as XGBoost, cuML, and others.
By the end of this training, participants will be able to:
- Set up the necessary development environment to build data models with NVIDIA RAPIDS.
- Understand the features, components, and benefits of RAPIDS.
- Leverage GPUs to accelerate end-to-end data and analytics pipelines.
- Implement GPU-accelerated data preparation and ETL processes using cuDF and Apache Arrow.
- Learn how to perform machine learning tasks with XGBoost and cuML algorithms.
- Build data visualisations and carry out graph analysis using cuXfilter and cuGraph.
