Image by author
Join KDnuggets with our Back to Basics journey to launch a new career or hone your data science skills. The Back to Basics course is divided into 4 weeks with a bonus week. We hope you can use these blogs as a course guide.
If you haven’t already, take a look at:
Moving on to week three, we’ll cover advanced topics and deployment.
- Day 1: Explore neural networks
- Day 2: Introduction to Deep Learning Libraries: PyTorch and Lightening AI
- Day 3: Getting started with PyTorch in 5 steps
- Day 4: Building a convolutional neural network with PyTorch
- Day 5: Introduction to Natural Language Processing
- Day 6: Deploy your first machine learning model
- Day 7: Introduction to Cloud Computing for Data Science
Week 4 – Part 1: Exploring neural networks
Unlocking the Power of AI: A Guide to Neural Networks and Their Applications.
Imagine a machine that thinks, learns and adapts like the human brain and discovers hidden patterns in data.
The algorithms in this technology, neural networks (NN), mimic cognition. We will later explore what NNs are and how they work.
In this article, I will explain the fundamental aspects of neural networks (NN): structure, types, real-world applications and key terms defining how they work.
Week 4 – Part 2: Introduction to Deep Learning Libraries: PyTorch and Lightning AI
A simple explanation of PyTorch and Lightning AI.
Deep Learning is a branch of the machine learning model based on neural networks. In the other machine model, data processing to find meaningful features is often done manually or by relying on domain expertise; However, deep learning can mimic the human brain to discover essential features, thereby increasing model performance.
There are many applications for deep learning models, including facial recognition, fraud detection, speech synthesis, text generation, and many more. Deep learning has become a standard approach in many advanced machine learning applications, and we have nothing to lose by learning more.
To develop this deep learning model, there are different library frameworks that we can rely on rather than starting from scratch. In this article, we will discuss two different libraries that we can use to develop deep learning models: PyTorch and Lighting AI.
Week 4 – Part 3: Getting started with PyTorch in 5 steps
This tutorial provides an in-depth introduction to machine learning using PyTorch and its high-level wrapper, PyTorch Lightning. The article covers essential steps from setup to advanced topics, providing a hands-on approach to building and training neural networks, and emphasizing the benefits of using Lightning.
PyTorch is a popular open-source machine learning framework based on Python and optimized for GPU-accelerated computing. Originally developed by Meta AI in 2016 and now part of the Linux Foundation, PyTorch has quickly become one of the most widely used frameworks for research and deep learning applications.
PyTorch Lightning is a lightweight wrapper built on top of PyTorch that further simplifies the researcher workflow and model development process. With Lightning, data scientists can focus more on building models rather than boilerplate code.
Week 4 – Part 4: Building a convolutional neural network with PyTorch
This blog post provides a tutorial on building a convolutional neural network for image classification in PyTorch, leveraging convolutional and pooling layers for feature extraction as well as fully connected layers for prediction.
A convolutional neural network (CNN or ConvNet) is a deep learning algorithm specifically designed for tasks where object recognition is crucial, such as image classification, detection, and segmentation. CNNs are capable of achieving state-of-the-art accuracy on complex vision tasks, powering many real-world applications such as surveillance systems, warehouse management, and more.
As humans, we can easily recognize objects in images by analyzing patterns, shapes and colors. CNNs can also be trained to perform this recognition, by learning which patterns are important for differentiation. For example, when we try to distinguish between a photo of a cat and a dog, our brain focuses on the unique shape, textures, and facial features. A CNN learns to detect these same types of distinctive features. Even for very fine-grained categorization tasks, CNNs are capable of learning complex feature representations directly from pixels.
Week 4 – Part 5: Introduction to Natural Language Processing
An overview of natural language processing (NLP) and its applications.
We are learning a lot about ChatGPT and Large Language Models (LLM). Natural language processing is an interesting topic, one that is currently taking the world of AI and technology by storm. Yes, LLMs like ChatGPT have contributed to their growth, but wouldn’t it be good to understand where it all comes from? So let’s get back to the basics: NLP.
NLP is a subfield of artificial intelligence, and it is the ability of a computer to detect and understand human language, through speech and text, just as we humans can do . NLP helps models process, understand and produce human language.
The goal of NLP is to bridge the communication gap between humans and computers. NLP models are typically trained on tasks such as next word prediction, allowing them to create contextual dependencies and then be able to generate relevant results.
Week 4 – Part 6: Deploy your first machine learning model
In just 3 simple steps, you can create and deploy a glass classification model faster than you can say… glass classification model!
In this tutorial, we will learn how to build a simple multi-classification model using the Glass classification database. Our goal is to develop and deploy a web application capable of predicting different types of glass, such as:
- Creating the Processed Windows Float
- Creating windows with non-floating processing
- Vehicle window float treated
- Non-floating vehicle windows processed (missing in dataset)
- Containers
- Dishes
- Headlights
Additionally, we will learn:
- Skops: share your scikit-learn based models and put them into production.
- Gradio: ML web application framework.
- HuggingFace Spaces: Free machine learning model and app hosting platform.
By the end of this tutorial, you will have hands-on experience building, training, and deploying a basic machine learning model as a web application.
Week 4 – Part 7: Introduction to Cloud Computing for Data Science
And the Power Duo of modern technology.
In today’s world, two main forces have emerged to change the game: data science and cloud computing.
Imagine a world where colossal amounts of data are generated every second. Well… you don’t have to imagine… It’s our world!
From social media interactions to financial transactions, from health records to e-commerce preferences, data is everywhere.
But what good is this data if we can’t derive value from it? This is exactly what Data Science does.
And where do we store, process and analyze this data? This is where Cloud Computing shines.
Let’s embark on a journey to understand the intertwined relationship between these two technological marvels. Let’s try to figure it all out together!
Congratulations on completing week 4!!
The KDnuggets team hopes that the Back to Basics journey has provided readers with a comprehensive and structured approach to mastering the fundamentals of data science.
The bonus week will be released next week Monday – stay tuned!
Nisha Arya is a Data Scientist and independent technical writer. She is particularly interested in providing data science career advice or tutorials and theoretical knowledge around data science. She also wants to explore the different ways in which artificial intelligence is/can benefit the longevity of human life. A passionate learner, looking to expand her technical knowledge and writing skills, while helping to mentor others.
