May 1, 2024
3 minute read
The Modified National Institute of Standards and Technology (MNIST) database is a large collection of handwritten digits that is often used for training and testing machine learning algorithms. The MNIST database is a subset of a larger database of handwritten digits that was collected by the National Institute of Standards and Technology (NIST). The MNIST database contains 70,000 images of handwritten digits, each of which is 28 pixels by 28 pixels. The digits are centered in the images and are written in black ink on a white background.
Why Learn MNIST?
n12ddz|
Find a path to becoming a MNIST. Learn more at:
OpenCourser.com/topic/n12ddz/mnis
Reading list
We've selected 12 books
that we think will supplement your
learning. Use these to
develop background knowledge, enrich your coursework, and gain a
deeper understanding of the topics covered in
MNIST.
Comprehensive guide to MNIST, including its history, data format, and various recognition techniques. It provides a well-rounded understanding of MNIST for both beginners and experienced researchers.
Introduces the fundamental concepts of machine learning using a practical approach. It includes a section on MNIST, where readers can gain hands-on experience in building and training machine learning models.
Provides a practical guide to machine learning using popular libraries such as Scikit-Learn, Keras, and TensorFlow. It includes a chapter on MNIST, covering data preparation, model training, and evaluation.
Includes a chapter on MNIST, discussing image processing techniques and their application in handwritten digit recognition. It provides a solid foundation for understanding the challenges and approaches involved in computer vision.
Covers a wide range of topics in pattern recognition and machine learning, including a chapter on MNIST. It provides a theoretical and mathematical perspective on the topic, with a focus on statistical methods and Bayesian approaches.
Beginner-friendly introduction to machine learning using Python. It includes a chapter on MNIST, covering data exploration, model training, and evaluation.
Classic introduction to reinforcement learning, which subfield of machine learning concerned with learning how to make decisions in an environment. Although MNIST is not a major focus of the book, it is mentioned in the context of using reinforcement learning for image classification.
Comprehensive reference on statistical learning, which subfield of machine learning focused on using statistical methods for prediction and estimation. It includes a chapter on MNIST, discussing different approaches to handwritten digit recognition.
Comprehensive guide to natural language processing using Python. Although it does not specifically cover MNIST, it provides a solid foundation for understanding text data and machine learning techniques, which are relevant to handwritten digit recognition.
Comprehensive guide to generative adversarial networks (GANs), which are a type of deep learning model used for generating new data. Although MNIST is not a major focus of the book, it is mentioned in the context of using GANs for image generation.
Beginner-friendly introduction to machine learning. Although it does not specifically cover MNIST, it provides a solid foundation for understanding the basic concepts and algorithms used in handwritten digit recognition.
Collection of recipes for implementing machine learning algorithms in Python. Although it does not have a dedicated recipe for MNIST, it includes recipes for related tasks such as image classification and neural networks.
For more information about how these books relate to this course, visit:
OpenCourser.com/topic/n12ddz/mnis
Save
