This document defines key concepts related to machine learning including artificial intelligence, machine learning, deep learning, training models, and learning types. It then discusses Core ML, which allows integrating machine learning models into apps. Core ML provides a unified representation for models and APIs to make predictions and train models on a user's device using domain-specific frameworks for vision, natural language, speech, sound, and more.
2. DEFINITIONS
• Artificial Intelligence, or AI, is the power added to a machine programmatically
to mimic human actions and thoughts.
• Machine Learning, or ML, is a subset of AI that trains machines to perform
certain tasks. For example, you can use ML to train a machine to recognize a cat
in an image or translate text from one language to another with prediction and
classification.
• Deep learning is a subset of machine learning where algorithms are created and
function similarly to machine learning, but there are many levels of these
algorithms, each providing a different interpretation of the data it conveys. This
network of algorithms is called artificial neural networks. In simple words, it
resembles the neural connections that exist in the human brain.
3. TRANING MODEL
• Training Model : The result of applying a machine-learning algorithm to a set of
training data”.
• Think of a Model as a function that takes an input, performs a particular
operation to its best on the given input, such as learning and then predicting and
classifying, and produces the suitable output with every new input received
.
4. LEARNING TYPES
• Supervised learning: is often described as task-oriented because of this. It is
highly focused on a singular task, feeding more and more examples to the
algorithm until it can accurately perform on that task.
- Examples:
Advertisement Popularity: Selecting advertisements that will perform well is
often a supervised learning task using cookies or any etc...
Face Recognition: Do you use Facebook? Most likely your face has been used in
a supervised learning algorithm that is trained to recognize your face.
Spam Classification: If you use a modern email system “Outlook”, chances are
you’ve encountered a spam filter.
5.
6. LEARNING TYPES
• Unsupervised Learning: Unsupervised learning is very much the opposite of
supervised learning. It features no labels. Instead, our algorithm would be fed a
lot of data and given the tools to understand the properties of the data. From
there, it can learn to group, cluster, and/or organize the data in a way such that a
human (or other intelligent algorithm) can come in and make sense of the newly
organized data.
Recommender Systems: If you’ve ever used YouTube or Netflix, you’ve most
likely encountered a video recommendation system.
Buying Habits: It is likely that your buying habits are contained in a database
somewhere and that data is being bought and sold actively at this time, like
Amazon, BestBuy etc.
7.
8. CORE ML
• Core ML : Integrate machine learning models into your app. Core ML provides a
unified representation for all models. Your app uses Core ML APIs and user data
to make predictions, and to train or fine-tune models, all on the user’s device.
• Core ML works with domain-specific frameworks.
• Utilize ML Models, ability to convert data to inside.
• Uses open-source software library for machine learning. It can be used across a
range of tasks but has a particular focus on training and inference of deep neural
networks. TensorFlow is a symbolic math library based on dataflow and
differentiable.
• Usage like Document classifier – Image Recognition – speech…
9. • Core ML is the foundation for domain-specific frameworks and functionality, it supports:
• Vision for analyzing images- Object Detection.
• Natural Language processing for text, Spell check, autocomplete.
• Speech for converting audio to text, Siri, Amazon Alexa.
• Sound Analysis for identifying sounds in audio, Shazam, Sound Radars.
• Shaders: Optimize graphics and compute performance with kernels
that are fine-tuned for the unique characteristics of each Metal
GPU family.
• Accelerate: BNNS library is a collection of functions that you use to construct
neural networks for training and inference. The library provides routines optimized for high performance and low-energy
consumption across all CPUs that the macOS, iOS, tvOS, and watchOS platforms support.
10. Models are in Core ML format and can be integrated into Xcode projects. You can select different versions
of models to optimize for sizes and architectures.