What is AI in machine learning?
 |
| Machine learning |
Machine learning (ML) is a branch of artificial intelligence (AI) focused on enabling computers and machines to imitate the way that humans learn, to perform tasks autonomously, and to improve their performance and accuracy through experience and exposure to more data. Machine learning is a branch of artificial intelligence that enables algorithms to automatically learn from data without being explicitly programmed. Its practitioners train algorithms to identify data patterns and make decisions with minimal human intervention. Machine learning has gone from a niche academic interest to a central part of the tech industry in the past two decades. It has given us self-driving cars, speech and image recognition, effective web search, fraud detection, a vastly improved understanding of the human genome, and many other advances. Amid this explosion of applications, there is a shortage of qualified data scientists, analysts, and machine learning engineers, making them some of the world’s most in-demand professionals.
What Is Machine Learning?
Machine learning (ML) is the subset of artificial intelligence that focuses on building systems that learn and improve as they consume more data. Artificial intelligence is a broader term that refers to systems or machines that mimic human intelligence. Machine learning and AI are often discussed together, and the terms are sometimes used interchangeably, but they don’t mean the same thing. In short, all machine learning is AI, but not all AI is machine learning.
Key Takeaways
- Machine learning is a subset of AI.
- The four most common types of machine learning are supervised, unsupervised, semi-supervised, and reinforcement.
- Popular types of machine learning algorithms include neural networks, decision trees, clustering, and random forests.
- Common machine learning use cases in business include object identification and classification, anomaly detection, document processing, and predictive analysis.
Machine learning (ML)
Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Within a subdiscipline in machine learning, advances in the field of deep learning have allowed neural networks, a class of statistical algorithms, to surpass many previous machine learning approaches in performance. ML finds application in many fields, including natural language processing, computer vision, speech recognition, email filtering, agriculture, and medicine. The application of ML to business problems is known as predictive analytics. Statistics and mathematical optimization (mathematical programming) methods comprise the foundations of machine learning. Data mining is a related field of study, focusing on exploratory data analysis (EDA) via unsupervised learning. From a theoretical viewpoint, probably approximately correct learning provides a framework for describing machine learning.
 |
| Artificial Intelligence (AI) |
Artificial intelligence
Machine learning emerged as a scientific pursuit stemming from the desire to develop artificial intelligence (AI). In the initial stages of AI as a scholarly field, certain researchers sought to enable machines to learn from data. They explored this challenge using various symbolic techniques, alongside early forms of "neural networks," primarily consisting of perceptrons and other models that were later recognized as reconfigurations of generalized linear models in statistics. Additionally, probabilistic reasoning found application, particularly in automated medical diagnostics. However, a growing focus on logical, knowledge-based methodologies created a divide between AI and machine learning. Probabilistic systems faced significant theoretical and practical challenges related to data acquisition and representation. By the 1980s, expert systems had become the predominant focus within AI, leading to a decline in the popularity of statistical approaches. Although research on symbolic and knowledge-based learning persisted within AI, culminating in inductive logic programming (ILP), the more statistically oriented research shifted outside the core AI domain, finding its place in pattern recognition and information retrieval. Concurrently, neural network research was largely abandoned by the fields of AI and computer science. This area continued under the label of "connectionism," pursued by researchers from various disciplines, including John Hopfield, David Rumelhart, and Geoffrey Hinton. Their notable achievement occurred in the mid-1980s with the revival of backpropagation. In the 1990s, machine learning (ML) was restructured and acknowledged as an independent field, transitioning its focus from the pursuit of artificial intelligence to addressing practical, solvable problems. This shift involved moving away from the symbolic methods inherited from AI and embracing techniques and models derived from statistics, fuzzy logic, and probability theory.
Machine learning versus deep learning versus neural networks
Since deep learning and machine learning tend to be used interchangeably, it’s worth noting the nuances between the two. Machine learning, deep learning, and neural networks are all subfields of artificial intelligence. However, neural networks is actually a sub-field of machine learning, and deep learning is a sub-field of neural networks. How deep learning and machine learning differ is in how each algorithm learns. "Deep" machine learning can use labeled datasets, also known as supervised learning, to inform its algorithm, but it doesn’t necessarily require a labeled dataset. The deep learning process can ingest unstructured data in its raw form (e.g., text or images), and it can automatically determine the set of features that distinguish different categories of data from one another. Neural networks, or artificial neural networks (ANNs), are comprised of node layers, containing an input layer, one or more hidden layers, and an output layer. Each node, or artificial neuron, connects to another and has an associated weight and threshold. If the output of any individual node is above the specified threshold value, that node is activated, sending data to the next layer of the network. Otherwise, no data is passed along to the next layer of the network by that node. The “deep” in deep learning refers to the number of layers in a neural network. A neural network that consists of more than three layers, which would be inclusive of the input and the output, can be considered a deep learning algorithm or a deep neural network. A neural network that only has three layers is just a basic neural network.
Common machine learning algorithms
Some machine learning algorithms are commonly used. These include:
Neural networks
Neural networks simulate the way the human brain works, with a huge number of linked processing nodes. Neural networks are good at recognizing patterns and play an important role in applications including natural language translation, image recognition, speech recognition, and image creation.
Linear regression
This algorithm is used to predict numerical values, based on a linear relationship between different values. For example, the technique could be used to predict house prices based on historical data for the area.
Clustering
Using unsupervised learning, clustering algorithms can identify patterns in data so that it can be grouped. Computers can help data scientists by identifying differences between data items that humans have overlooked.
Logistic regression
This supervised learning algorithm makes predictions for categorical response variables, such as “yes/no” answers to questions. It can be used for applications such as classifying spam and quality control on a production line.
Random forests
In a random forest, the machine learning algorithm predicts a value or category by combining the results from several decision trees.
Decision trees
Decision trees can be used for both predicting numerical values (regression) and classifying data into categories. Decision trees use a branching sequence of linked decisions that can be represented with a tree diagram. One of the advantages of decision trees is that they are easy to validate and audit, unlike the black box of the neural network.
AI and ML in Real-world Applications
Healthcare
Artificial intelligence (AI) and machine learning (ML) play a crucial role in disease diagnosis, forecasting patient outcomes, and tailoring treatment plans. A notable instance is IBM Watson, which evaluates medical data to suggest appropriate treatment alternatives.
Finance
In the finance sector, machine learning algorithms are employed to identify fraudulent activities, streamline trading strategies, and offer personalized recommendations to customers.
Retail
In retail, AI-driven recommendation systems examine consumer behavior to recommend products effectively.
Autonomous Vehicles
Autonomous vehicles utilize machine learning for identifying objects, planning routes, and making decisions.
Natural Language Processing (NLP)
Artificial intelligence analyzes human language for applications such as chatbots, language translation, and sentiment analysis.
How to choose the right AI platform for machine learning
Selecting a platform can be a challenging process, as the wrong system can drive up costs, or limit the use of other valuable tools or technologies. When reviewing multiple vendors to select an AI platform, there is often a tendency to think that more features a better. Maybe so, but reviewers should start by thinking through what the AI platform will be doing for their organization. What machine learning capabilities need to be delivered, and what features are important to accomplish them? One missing feature might doom the usefulness of an entire system. Here are some features to consider.
MLOps functionalities. Does the system possess:
- a unified interface for ease of management?
- Automated machine learning tools for faster model creation with low-code and no-code functionality?
- Decision optimization to streamline the selection and deployment of optimization models?
- Visual modeling to combine visual data science with open-source libraries and notebook-based interfaces on a unified data and AI studio?
- Automated development for beginners to get started quickly, and more advanced data scientists to experiment?
- Synthetic data generator as an alternative or supplement to real-world data when real-world data is not readily available?
Generative AI functionalities. Does the system possess:
- A content generator that can generate text, images, and other content based on the data it was trained on?
- Automated classification to read and classify written input, such as evaluating and sorting customer complaints or reviewing customer feedback sentiment?
- a summary generator that can transform dense text into a high-quality summary, capture key points from financial reports, and generate meeting transcriptions?
- a data extraction capability to sort through complex details and quickly pull the necessary information from large documents?
How Machine Learning Works
As its name indicates, machine learning works by creating computer-based statistical models that are refined for a given purpose by evaluating training data, rather than by the classical approach, where programmers develop a static algorithm that attempts to solve a problem. As data sets are put through the ML model, the resulting output is judged on accuracy, allowing data scientists to adjust the model through a series of established variables, called hyperparameters, and algorithmically adjusted variables, called learning parameters. Because the algorithm adjusts as it evaluates training data, the process of exposure and calculation around new data trains the algorithm to become better at what it does. The algorithm is the computational part of the project, while the term “model” is a trained algorithm that can be used for real-world use cases. The scope, resources, and goals of machine learning projects will determine the most appropriate path, but most involve a series of steps.
Gather and compile data
Training ML models requires a lot of high-quality data. Finding it is sometimes difficult, and labeling it, if necessary, can be very resource-intensive. After identifying potential data sources, evaluate them to determine overall quality and alignment with the project’s existing data integration/repository resources. Those sources form the training foundation of a machine learning project.
Refine and prepare data for analysis
Chances are that incoming data won’t be ready to go. Data preparation cleans up data sets to ensure that all records can be easily ingested during training. Preparation includes a range of transformation tasks, such as establishing date and time formats, joining or separating columns as needed, and setting other format parameters, such as acceptable significant digits in real number data. Other key tasks include cleaning out duplicate records, also called data deduplication, and identifying and possibly removing outliers.
Assess model performance and accuracy
After the model has been trained to sufficient accuracy, it’s time to give it previously unseen data to test how it performs. Often, the data used for testing is a subset of the training dataset set aside for use after initial training.
Educate the model through training
Once the desired final model has been selected, the training process begins. In training, a curated data set, either labeled or unlabeled, is fed to the algorithm. In initial runs, outcomes may not be great, but data scientists will tweak as needed to refine performance and increase accuracy. Then the algorithm is shown data again, usually in larger quantities, to tune it more precisely. The more data the algorithm sees, the better the final model should become at delivering the desired results.
Refine and prepare data for analysis
Chances are that incoming data won’t be ready to go. Data preparation cleans up data sets to ensure that all records can be easily ingested during training. Preparation includes a range of transformation tasks, such as establishing date and time formats, joining or separating columns as needed, and setting other format parameters, such as acceptable significant digits in real number data. Other key tasks include cleaning out duplicate records, also called data deduplication, and identifying and possibly removing outliers.
Benefits of Machine Learning
Personalization and Innovation in Services:
Machine learning has opened a new door for customer experiences through personalization. Purchase history, browsing history, demographic data, and additional information can be used to build an individual customer profile, which then can be cross-referenced against similar profiles to make predictions about customer interests. This allows for suggestion engine offerings, auto-generated discounts, and other types of personalized engagement to keep customers returning.
Streamlining Decision-Making and Predictive Analysis:
Data-driven decisions start with data analysis. That’s an obvious statement, but when done manually, the analysis process is time- and resource-intensive and may not yield rich enough insights to justify the cost. Machine learning can comb through large volumes of data to identify trends and patterns so that users can focus on queries and actionable results rather than optimizing manual data processing. Depending on the analytics tool, machine learning can generate predictions and identify hard-to-find insights in the data, allowing for a greater depth of analysis and more value to the organization.
Boosting Efficiency and Automating Tasks:
Machine learning is at the root of many of the technologies that make workers more efficient. Many low-cognition, repetitive tasks—including spell-checking as well as document digitization and classification—are now done by computers, thanks to machine learning. Machine learning also excels at the lightning-fast, in-the-moment data analysis that’s extremely difficult for humans. Is that transaction fraudulent, or is that email a phishing scam? Machine learning systems can often accurately determine the answer in seconds and automatically take appropriate measures. By combining ML technologies, predictions can be made from data, accompanied by explanations of the factors that influenced the prediction, helping executives chart the best paths for their organizations.
Challenges in Artificial Intelligence and Machine Learning
While AI and machine learning offer numerous benefits, they also encounter several challenges, including:
- Data Bias: Inaccurate or low-quality data can result in biased outcomes.
- Explainability: The decision-making processes of AI systems are frequently hard to understand.
- Computational Power: The training of machine learning models demands substantial computational resources.
- Security Threats: AI models may be susceptible to adversarial attacks.
Machine Learning FAQs
1. What is machine learning?
Machine learning is a branch of artificial intelligence that enables algorithms to automatically learn from data without being explicitly programmed. Its practitioners train algorithms to identify data patterns and make decisions with minimal human intervention. Machine learning has gone from a niche academic interest to a central part of the tech industry in the past two decades. It has given us self-driving cars, speech and image recognition, effective web search, fraud detection, a vastly improved understanding of the human genome, and many other advances. Amid this explosion of applications, there is a shortage of qualified data scientists, analysts, and machine learning engineers, making them some of the world’s most in-demand professionals.
2. What is Machine Learning Specialization about?
The Machine Learning Specialization is a foundational online program created in collaboration between DeepLearning.AI and Stanford Online. This beginner-friendly program will teach you the fundamentals of machine learning and how to use these techniques to build real-world AI applications. This Specialization is taught by Andrew Ng, an AI pioneer who has led critical research at Stanford University and groundbreaking work at Google Brain, Baidu, and Landing.AI to advance the AI field. This 3-course Specialization is an updated and expanded version of Andrew’s pioneering Machine Learning course, rated 4.9 out of 5 and taken by over 4.8 million learners since it launched in 2012. It provides a broad introduction to modern machine learning, including supervised learning (multiple linear regression, logistic regression, neural networks, and decision trees), unsupervised learning (clustering, dimensionality reduction, recommender systems), and some of the best practices used in Silicon Valley for artificial intelligence and machine learning innovation (evaluating and tuning models, taking a data-centric approach to improving performance, and more.) By the end of this Specialization, you will have mastered key concepts and gained the practical know-how to quickly and powerfully apply machine learning to challenging real-world problems. If you’re looking to break into AI or build a career in machine learning, the new Machine Learning Specialization is the best place to start.
3. What background knowledge is necessary for the Machine Learning Specialization?
Learners should understand basic coding (for loops, functions, if/else statements) and high school-level math (arithmetic, algebra). Any additional math concepts will be explained along the way.
4. What makes the Machine Learning Specialization so unique?
The Machine Learning Specialization is a foundational online program taught by Andrew Ng, an AI pioneer who has led critical research at Stanford University and groundbreaking work at Google Brain, Baidu, and Landing.AI to advance the AI field. This 3-course Specialization is an updated and expanded version of Andrew’s pioneering Machine Learning course, rated 4.9 out of 5 and taken by over 4.8 million learners since it launched in 2012. This program has been designed to teach you foundational machine learning concepts without prior math knowledge or a rigorous coding background. Unlike the original course, which required some knowledge of math, the new Specialization aptly balances intuition, code practice, and mathematical theory to create a simple and effective learning experience for first-time students.
5. How do I take the Specialization?
You can enroll in the Machine Learning Specialization on Coursera. You will watch videos and complete assignments on Coursera as well.
6. Will I receive a certificate at the end of the Specialization?
You will receive a certificate at the end of each course if you pay for the courses and complete the programming assignments. There is a limit of 180 days of certificate eligibility, after which you must re-purchase the course to obtain a certificate. If you audit the course for free, you will not receive a certificate. If you complete all 4 courses and are subscribed to the Specialization, you will also receive an additional certificate showing that you completed the entire Specialization.
