Image by author
Join KDnuggets' Back to Basics Pathway to jump-start your new career or sharpen your data science skills. The Back to Basics pathway is divided into four weeks, including a bonus week. We hope you will use these blogs as a course guide.
If you haven't seen it yet, check it out below.
Week 3 covers advanced topics and developments.
- Day 1: Exploring neural networks
- Day 2: Deep learning library overview: PyTorch and Lightening AI
- Day 3: Get started with PyTorch in 5 steps
- Day 4: Building Convolutional Neural Networks with PyTorch
- Day 5: Overview of 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
Unleashing the power of AI: A guide to neural networks and their applications.
Imagine machines thinking, learning, and adapting like human brains, discovering hidden patterns in data.
This technology, Neural Network (NN) algorithms, mimics cognition. We will explain later what NN is and how it works.
This article describes the basic aspects of neural networks (NNs): important terms that define their structure, types, practical applications, and operations.
Week 4 – Part 2: Deep Learning Library Overview: PyTorch and Lightning AI
A quick introduction to PyTorch and Lightning AI.
Deep learning is a branch of machine learning models based on neural networks. In another machine model, data processing to find meaningful features is often done manually or relies on domain expertise. However, deep learning can mimic the human brain to discover important features and improve model performance.
Deep learning models have many applications, including facial recognition, fraud detection, speech-to-text, and text generation. Deep learning has become a standard approach in many advanced machine learning applications, so you have nothing to lose by learning about it.
To develop this deep learning model, there are various library frameworks that you can rely on instead of starting from scratch. This article describes two different libraries that you can use to develop deep learning models: PyTorch and Lighting AI.
Week 4 – Part 3: Get started with PyTorch in 5 steps
This tutorial provides an in-depth look at machine learning using PyTorch and its high-level wrapper, PyTorch Lightning. This article covers important steps from installation to advanced topics, provides a practical approach to building and training neural networks, and highlights 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 deep learning research and applications.
PyTorch Lightning is a lightweight wrapper built on top of PyTorch that further simplifies researchers' workflows and model development processes. Lightning lets data scientists focus on designing models instead of boilerplate code.
Week 4 – Part 4: Building Convolutional Neural Networks 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, and fully connected layers for prediction.
Convolutional neural networks (CNNs or ConvNets) are deep learning algorithms specifically designed for tasks where object recognition is important, such as image classification, detection, and segmentation. CNNs can achieve state-of-the-art accuracy in complex vision tasks, powering many real-world applications such as surveillance systems and warehouse management.
Humans 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 trying to distinguish between a photo of a cat and a photo of a dog, our brains focus on unique shapes, textures, and facial features. CNNs learn to recognize these same types of salient features. Even for very fine-grained classification tasks, CNNs can learn 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're learning a lot about ChatGPT and Large-Scale Language Models (LLM). Natural language processing is an interesting topic and one that is currently taking the world of AI and technology by storm. Sure, LLMs like ChatGPT have contributed to its growth, but wouldn't it be good to understand where it came from? So let's get back to the basics: NLP.
NLP is a subfield of artificial intelligence and is the ability of computers to detect and understand human language through speech and text, just as humans do. NLP helps models process, understand, and output 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 build contextual dependencies and produce relevant output.
Week 4 – Part 6: Deploy your first machine learning model
In just 3 easy steps, you can build and deploy a glass classification model faster than you can say…Glass Classification Model!
In this tutorial, you will learn how to build a simple multi-classification model using a Glass classification dataset. Our goal is to develop and deploy a web application that can predict different types of glass, including:
- Build window float processed
- Constructing a non-floating window
- Car window float processed
- Vehicle window non-float processing (missing in dataset)
- container
- tableware
- head lamp
Additionally, you will learn about:
- Skops: Share scikit-learn based models and bring them to production.
- Gradio: ML web application framework.
- HuggingFace Spaces: Free machine learning model and application hosting platform.
After completing this tutorial, you will have hands-on experience building, training, and deploying basic machine learning models as web applications.
Week 4 – Part 7: Introduction to Cloud Computing for Data Science
And a power duo of modern technology.
In today's world, two major forces are emerging as game changers: data science and cloud computing.
Imagine a world where vast amounts of data are generated every second. Well…no need to imagine…it’s our world!
From social media interactions to financial transactions, medical records to e-commerce preferences, data is everywhere.
But what good is this data if you can't get the value? That's exactly what data science does.
And where do you store, process, and analyze this data? That's where cloud computing comes into play.
Take a journey to understand the intertwined relationship between these two technological wonders. Let's find it together!
Congratulations on completing week 4!!
The team at KDnuggets hopes that the “Back to Basics” pathway provides readers with a comprehensive and structured approach to mastering the fundamentals of data science.
Bonus week will be posted next Monday, so stay tuned!
Nisha Arya I'm a data scientist, freelance technical writer, editor and community manager at KDnuggets. She has a particular interest in providing advice and tutorials on careers in data science, as well as theory-based knowledge about data science. Nisha covers a wide range of topics and is interested in exploring the different ways in which artificial intelligence can benefit human longevity. An avid learner, Nisha aims to expand her technology knowledge and writing skills while helping to mentor others.
