Welcome
IPN-Dharma AI Lab
This is an IPN CIC - DHARMA initiative to provide an Artificial Intelligence Laboratory to motivate researchers, professors and students to take advantage of the courses, resources and tools of the main technology platforms of the industry in the areas of Machine Learning, Data Science, Cloud Computing, Artificial Intelligence and Internet of Things with the purpose of generating a practical experience through a learning model between peers and by objectives.
Level 2: Contextual Knowledge
Create Machine Learning Models
From the most basic classical machine learning models, to exploratory data analysis and customizing architectures, you’ll be guided by easy to digest conceptual content and interactive Jupyter notebooks, all without leaving your browser.
Create Machine Learning Models is a subset of the complete learning path Foundations of Data Science for Machine Learning for people with some experience or a strong mathematical background.
If you already have some idea what machine learning is about or you have a strong mathematical background you may best enjoy jumping right in to the Create Machine Learning Models learning path. These modules teach some machine learning concepts, but move fast so they can get to the power of using tools like scikit-learn, TensorFlow, and PyTorch. This learning path is also the best one for you if you're looking for just enough familiarity to understand machine learning examples for products like Azure ML or Azure Databricks.
Create Machine Learning Models is a subset of the complete learning path Foundations of Data Science for Machine Learning for people with some experience or a strong mathematical background.
If you already have some idea what machine learning is about or you have a strong mathematical background you may best enjoy jumping right in to the Create Machine Learning Models learning path. These modules teach some machine learning concepts, but move fast so they can get to the power of using tools like scikit-learn, TensorFlow, and PyTorch. This learning path is also the best one for you if you're looking for just enough familiarity to understand machine learning examples for products like Azure ML or Azure Databricks.
Courses in this program
1) Explore and Analyze Data with Python
Data exploration and analysis is at the core of data science. Data scientists require skills in languages like Python to explore, visualize, and manipulate data.
In this module, you will learn:
In this module, you will learn:
- Common data exploration and analysis tasks.
- How to use Python packages like NumPy, Pandas, and Matplotlib to analyze data.
Estimated effort 1 hour
English language
2) Train and Evaluate Regression Models
Regression is a commonly used kind of machine learning for predicting numeric values.
In this module, you'll learn:
In this module, you'll learn:
- When to use regression models.
- How to train and evaluate regression models using the Scikit-Learn framework.
3) Train and Evaluate Classification Models
Classification is a kind of machine learning used to categorize items into classes.
In this module, you'll learn:
In this module, you'll learn:
- When to use classification.
- How to train and evaluate a classification model using the Scikit-Learn framework.
4) Train and Evaluate Clustering Models
Clustering is a kind of machine learning that is used to group similar items into clusters.
In this module, you'll learn:
In this module, you'll learn:
- When to use clustering.
- How to train and evaluate a clustering model using the scikit-learn framework.
5) Train and Evaluate Deep Learning Models
Deep learning is an advanced form of machine learning that emulates the way the human brain learns through networks of connected neurons.
In this module, you will learn:
In this module, you will learn:
- Basic principles of deep learning.
- How to train a deep neural network (DNN) using PyTorch or Tensorflow.
- How to train a convolutional neural network (CNN) using PyTorch or Tensorflow.
- How to use transfer learning to train a convolutional neural network (CNN) with PyTorch or Tensorflow.