What is Machine Learning? | IBM
Machine learning focuses on applications that learn from experience and improve their decision-making or predictive accuracy over time.
Machine learning is a branch of artificial intelligence (AI) focused on building applications that learn from data and improve their accuracy over time without being programmed to do so.
In data science, an algorithm is a sequence of statistical processing steps. In machine learning, algorithms are 'trained' to find patterns and features in massive amounts of data in order to make decisions and predictions based on new data. The better the algorithm, the more accurate the decisions and predictions will become as it processes more data.
Today, examples of machine learning are all around us. Digital assistants search the web and play music in response to our voice commands. Websites recommend products and movies and songs based on what we bought, watched, or listened to before. Robots vacuum our floors while we do . . . something better with our time. Spam detectors stop unwanted emails from reaching our inboxes. Medical image analysis systems help doctors spot tumors they might have missed. And the first self-driving cars are hitting the road.
We can expect more. As big data keeps getting bigger, as computing becomes more powerful and affordable, and as data scientists keep developing more capable algorithms, machine learning will drive greater and greater efficiency in our personal and work lives.
There are four basic steps for building a machine learning application (or model). These are typically performed by data scientists working closely with the business professionals for whom the model is being developed.
Training data is a data set representative of the data the machine learning model will ingest to solve the problem its designed to solve. In some cases, the training data is labeled datatagged to call out features and classifications the model will need to identify. Other data is unlabeled, and the model will need to extract those features and assign classifications on its own.
In either case, the training data needs to be properly preparedrandomized, de-duped, and checked for imbalances or biases that could impact the training. It should also be divided into two subsets: the training subset, which will be used to train the application, and the evaluation subset, used to test and refine it.
Again, an algorithm is a set of statistical processing steps. The type of algorithm depends on the type (labeled or unlabeled) and amount of data in the training data set and on the type of problem to be solved.
Common types of machine learning algorithms for use with labeled data include the following:
Algorithms for use with unlabeled data include the following:
Training the algorithm is an iterative processit involves running variables through the algorithm, comparing the output with the results it should have produced, adjusting weights and biases within the algorithm that might yield a more accurate result, and running the variables again until the algorithm returns the correct result most of the time. The resulting trained, accurate algorithm is the machine learning modelan important distinction to note, because 'algorithm' and 'model' are incorrectly used interchangeably, even by machine learning mavens.
The final step is to use the model with new data and, in the best case, for it to improve in accuracy and effectiveness over time. Where the new data comes from will depend on the problem being solved. For example, a machine learning model designed to identify spam will ingest email messages, whereas a machine learning model that drives a robot vacuum cleaner will ingest data resulting from real-world interaction with moved furniture or new objects in the room.
Machine learningmethods (also called machine learning styles) fall into three primary categories.
Supervised machine learning trains itself on a labeled dataset. That is, the data is labeled with information that the machine learning model is being built to determine and that may even be classified in ways the model is supposed to classify data. For example, a computer vision model designed to identify purebred German Shepherd dogs might be trained on a data set of various labeled dog images.
Supervised machine learning requires less training data than other machine learningmethods and makes training easier because the results of the model can be compared to actual labeled results. But, properly labeled data is expensive to prepare, and there's the danger of overfitting, or creating a model so closely tied and biased to the training data that it doesn't handle variations in new data accurately.
Learn more about supervised learning.
Unsupervised machine learning ingests unlabeled datalots and lots of itand uses algorithms to extract meaningful features needed to label, sort, and classify the data in real-time, without human intervention. Unsupervised learning is less about automating decisions and predictions, and more about identifying patterns and relationships in data that humans would miss. Take spam detection, for examplepeople generate more email than a team of data scientists could ever hope to label or classify in their lifetimes. An unsupervised learning algorithm can analyze huge volumes of emails and uncover the features and patterns that indicate spam (and keep getting better at flagging spam over time).
Learn more about unsupervised learning.
Semi-supervised learning offers a happy medium between supervised and unsupervised learning. During training, it uses a smaller labeled dataset to guide classification and feature extraction from a larger, unlabeled data set. Semi-supervised learning can solve the problem of having not enough labeled data (or not being able to afford to label enough data) to train a supervised learning algorithm.
Reinforcement machine learning is a behavioral machinelearning model that is similar to supervised learning, but the algorithm isnt trained using sample data. This model learns as it goes by using trial and error. A sequence of successful outcomes will be reinforced to develop the best recommendation or policy for a given problem.
The IBM Watson system that won the Jeopardy! challenge in 2011 makes a good example. The system used reinforcement learning to decide whether to attempt an answer (or question, as it were), which square to select on the board, and how much to wagerespecially on daily doubles.
Learn more about reinforcement learning.
Deep learning is a subset of machine learning (all deep learning is machine learning, but not all machine learning is deep learning). Deep learning algorithms define an artificial neural network that is designed to learn the way the human brain learns. Deep learning models require large amounts of data that pass through multiple layers of calculations, applying weights and biases in each successive layer to continually adjust and improve the outcomes.
Deep learning models are typically unsupervised or semi-supervised. Reinforcement learning models can also be deep learning models. Certain types of deep learning modelsincluding convolutional neural networks (CNNs) and recurrent neural networks (RNNs)are driving progress in areas such as computer vision, natural language processing (including speech recognition), and self-driving cars.
See the blog post AI vs. Machine Learning vs. Deep Learning vs. Neural Networks: Whats the Difference? for a closer look at how the different concepts relate.
Learn more about deep learning.
As noted at the outset, machine learning is everywhere. Here are just a few examples of machine learning you might encounter every day:
IBM Watson Machine Learning supports the machine learning lifecycle end to end. It is available in a range of offerings that let you build machine learning models wherever your data lives and deploy them anywhere in your hybrid multicloud environment.
IBM Watson Machine Learning on IBM Cloud Pak for Data helps enterprise data science and AI teams speed AI development and deployment anywhere, on a cloud native data and AI platform. IBM Watson Machine Learning Cloud, a managed service in the IBM Cloud environment, is the fastest way to move models from experimentation on the desktop to deployment for production workloads. For smaller teams looking to scale machine learning deployments, IBM Watson Machine Learning Server offers simple installation on any private or public cloud.
To get started, sign up for an IBMid and create your IBM Cloud account.
Go here to see the original:
What is Machine Learning? | IBM
- Predicting land suitability for wheat and barley crops using machine learning techniques - Nature - May 10th, 2025 [May 10th, 2025]
- AI and Machine Learning - Ribeiro Preto adopts Optibus to optimise public bus system - Smart Cities World - May 10th, 2025 [May 10th, 2025]
- Childrens Hospital Los Angeles Leads Development of First Machine Learning Tool to Predict Risk of Cisplatin-Induced Hearing Loss - Business Wire - May 10th, 2025 [May 10th, 2025]
- Google is using machine learning to help Android users avoid unwanted and dangerous notifications - BetaNews - May 10th, 2025 [May 10th, 2025]
- London School of Emerging Technology (LSET) Concludes International Workshop on Emerging AI & Machine Learning Innovation - Barchart.com - May 10th, 2025 [May 10th, 2025]
- Thermal performance, entropy generation, and machine learning insights of AlO-TiO hybrid nanofluids in turbulent flow - Nature - May 10th, 2025 [May 10th, 2025]
- Predicting the efficacy of bevacizumab on peritumoral edema based on imaging features and machine learning - Nature - May 10th, 2025 [May 10th, 2025]
- How AI and machine learning are supercharging video conferencing tools - European CEO - May 10th, 2025 [May 10th, 2025]
- The need for a risk-based approach to AI and machine learning in healthcare - Health Tech World - May 10th, 2025 [May 10th, 2025]
- Integrated bioinformatics, machine learning, and molecular docking reveal crosstalk genes and potential drugs between periodontitis and systemic lupus... - May 10th, 2025 [May 10th, 2025]
- Adversarial Machine Learning in Detecting Inauthentic Behavior on Social Platforms - AiThority - May 10th, 2025 [May 10th, 2025]
- Exploring crop health and its associations with fungal soil microbiome composition using machine learning applied to remote sensing data - Nature - May 10th, 2025 [May 10th, 2025]
- Trust-based model and machine learning improve forest fire detection system - International Fire & Safety Journal - May 10th, 2025 [May 10th, 2025]
- A machine learning engineer shares the rsums that landed her jobs at Meta and X and what she'd change if she applied again - Business Insider Africa - May 5th, 2025 [May 5th, 2025]
- Recentive Analytics v. Fox: The Federal Circuit Provides Analysis on the Patent Eligibility of Machine Learning Claims - Mintz - May 5th, 2025 [May 5th, 2025]
- A machine learning engineer shares the rsums that landed her jobs at Meta and X and what she'd change if she applied again - Business Insider - May 5th, 2025 [May 5th, 2025]
- Enhancing urban resilience through machine learning-supported flood risk assessment: integrating flood susceptibility with building function... - May 5th, 2025 [May 5th, 2025]
- MicroAlgo Inc. Develops Classifier Auto-Optimization Technology Based on Variational Quantum Algorithms, Accelerating the Advancement of Quantum... - May 5th, 2025 [May 5th, 2025]
- Enhanced metal ion adsorption using ZnO-MXene nanocomposites with machine learning-based performance prediction - Nature - May 5th, 2025 [May 5th, 2025]
- Integrating SHAP analysis with machine learning to predict postpartum hemorrhage in vaginal births - BMC Pregnancy and Childbirth - May 5th, 2025 [May 5th, 2025]
- Machine learning provide new insights into how the brain responds to heroin use - News-Medical - May 2nd, 2025 [May 2nd, 2025]
- Machine Learning and AI in Basic HIV Research: From Big Data Analysis to Large Language Models - UNC Gillings School of Global Public Health - May 2nd, 2025 [May 2nd, 2025]
- Machine learning brings new insights to cells role in addiction, relapse - University of Cincinnati - May 2nd, 2025 [May 2nd, 2025]
- UH/UC Researchers Use Machine Learning to Map Brain Changes from Heroin Addiction - University of Houston - May 2nd, 2025 [May 2nd, 2025]
- Machine Learning Algorithm Predicts Shiba Inu Price In May You Should See This - The Crypto Update - May 2nd, 2025 [May 2nd, 2025]
- Seerist partners with SOCOM to enhance AI and machine learning for special operations - Defence Industry Europe - May 2nd, 2025 [May 2nd, 2025]
- How machine learning can spark many discoveries in science and medicine - The Indian Express - April 30th, 2025 [April 30th, 2025]
- Machine learning frameworks to accurately estimate the adsorption of organic materials onto resin and biochar - Nature - April 30th, 2025 [April 30th, 2025]
- Gene Therapy Research Roundup: Gene Circuits and Controlling Capsids With Machine Learning - themedicinemaker.com - April 30th, 2025 [April 30th, 2025]
- Seerist and SOCOM Enter Five-Year CRADA to Advance AI and Machine Learning for Operations - PRWeb - April 30th, 2025 [April 30th, 2025]
- Machine learning models for estimating the overall oil recovery of waterflooding operations in heterogenous reservoirs - Nature - April 30th, 2025 [April 30th, 2025]
- Machine learning-based quantification and separation of emissions and meteorological effects on PM - Nature - April 30th, 2025 [April 30th, 2025]
- Protein interactions, network pharmacology, and machine learning work together to predict genes linked to mitochondrial dysfunction in hypertrophic... - April 30th, 2025 [April 30th, 2025]
- AQR Bets on Machine Learning as Asness Becomes AI Believer - Bloomberg.com - April 30th, 2025 [April 30th, 2025]
- Darktrace enhances Cyber AI Analyst with advanced machine learning for improved threat investigations - Industrial Cyber - April 21st, 2025 [April 21st, 2025]
- Infrared spectroscopy with machine learning detects early wood coating deterioration - Phys.org - April 21st, 2025 [April 21st, 2025]
- A simulation-driven computational framework for adaptive energy-efficient optimization in machine learning-based intrusion detection systems - Nature - April 21st, 2025 [April 21st, 2025]
- Machine learning model to predict the fitness of AAV capsids for gene therapy - EurekAlert! - April 21st, 2025 [April 21st, 2025]
- An integrated approach of feature selection and machine learning for early detection of breast cancer - Nature - April 21st, 2025 [April 21st, 2025]
- Predicting cerebral infarction and transient ischemic attack in healthy individuals and those with dysmetabolism: a machine learning approach combined... - April 21st, 2025 [April 21st, 2025]
- Autolomous CEO Discusses AI and Machine Learning Applications in Pharmaceutical Development and Manufacturing with Pharmaceutical Technology -... - April 21st, 2025 [April 21st, 2025]
- Machine Learning Interpretation of Optical Spectroscopy Using Peak-Sensitive Logistic Regression - ACS Publications - April 21st, 2025 [April 21st, 2025]
- Estimated glucose disposal rate outperforms other insulin resistance surrogates in predicting incident cardiovascular diseases in... - April 21st, 2025 [April 21st, 2025]
- Machine learning-based differentiation of schizophrenia and bipolar disorder using multiscale fuzzy entropy and relative power from resting-state EEG... - April 12th, 2025 [April 12th, 2025]
- Increasing load factor in logistics and evaluating shipment performance with machine learning methods: A case from the automotive industry - Nature - April 12th, 2025 [April 12th, 2025]
- Machine learning-based prediction of the thermal conductivity of filling material incorporating steelmaking slag in a ground heat exchanger system -... - April 12th, 2025 [April 12th, 2025]
- Do LLMs Know Internally When They Follow Instructions? - Apple Machine Learning Research - April 12th, 2025 [April 12th, 2025]
- Leveraging machine learning in precision medicine to unveil organochlorine pesticides as predictive biomarkers for thyroid dysfunction - Nature - April 12th, 2025 [April 12th, 2025]
- Analysis and validation of hub genes for atherosclerosis and AIDS and immune infiltration characteristics based on bioinformatics and machine learning... - April 12th, 2025 [April 12th, 2025]
- AI and Machine Learning - Bentley and Google partner to improve asset analytics - Smart Cities World - April 12th, 2025 [April 12th, 2025]
- Where to find the next Earth: Machine learning accelerates the search for habitable planets - Phys.org - April 10th, 2025 [April 10th, 2025]
- Concurrent spin squeezing and field tracking with machine learning - Nature - April 10th, 2025 [April 10th, 2025]
- This AI Paper Introduces a Machine Learning Framework to Estimate the Inference Budget for Self-Consistency and GenRMs (Generative Reward Models) -... - April 10th, 2025 [April 10th, 2025]
- UCI researchers study use of machine learning to improve stroke diagnosis, access to timely treatment - UCI Health - April 10th, 2025 [April 10th, 2025]
- Assessing dengue forecasting methods: a comparative study of statistical models and machine learning techniques in Rio de Janeiro, Brazil - Tropical... - April 10th, 2025 [April 10th, 2025]
- Machine learning integration of multimodal data identifies key features of circulating NT-proBNP in people without cardiovascular diseases - Nature - April 10th, 2025 [April 10th, 2025]
- How AI, Data Science, And Machine Learning Are Shaping The Future - Forbes - April 10th, 2025 [April 10th, 2025]
- Development and validation of interpretable machine learning models to predict distant metastasis and prognosis of muscle-invasive bladder cancer... - April 10th, 2025 [April 10th, 2025]
- From fax machines to machine learning: The fight for efficiency - HME News - April 10th, 2025 [April 10th, 2025]
- Carbon market and emission reduction: evidence from evolutionary game and machine learning - Nature - April 10th, 2025 [April 10th, 2025]
- Infleqtion Unveils Contextual Machine Learning (CML) at GTC 2025, Powering AI Breakthroughs with NVIDIA CUDA-Q and Quantum-Inspired Algorithms - Yahoo... - March 22nd, 2025 [March 22nd, 2025]
- Karlie Kloss' coding nonprofit offering free AI and machine learning workshop this weekend - KSDK.com - March 22nd, 2025 [March 22nd, 2025]
- Machine learning reveals distinct neuroanatomical signatures of cardiovascular and metabolic diseases in cognitively unimpaired individuals -... - March 22nd, 2025 [March 22nd, 2025]
- Machine learning analysis of cardiovascular risk factors and their associations with hearing loss - Nature.com - March 22nd, 2025 [March 22nd, 2025]
- Weekly Recap: Dual-Cure Inks, AI And Machine Learning Top This Weeks Stories - Ink World Magazine - March 22nd, 2025 [March 22nd, 2025]
- Network-based predictive models for artificial intelligence: an interpretable application of machine learning techniques in the assessment of... - March 22nd, 2025 [March 22nd, 2025]
- Machine learning aids in detection of 'brain tsunamis' - University of Cincinnati - March 22nd, 2025 [March 22nd, 2025]
- AI & Machine Learning in Database Management: Studying Trends and Applications with Nithin Gadicharla - Tech Times - March 22nd, 2025 [March 22nd, 2025]
- MicroRNA Biomarkers and Machine Learning for Hypertension Subtyping - Physician's Weekly - March 22nd, 2025 [March 22nd, 2025]
- Machine Learning Pioneer Ramin Hasani Joins Info-Tech's "Digital Disruption" Podcast to Explore the Future of AI and Liquid Neural Networks... - March 22nd, 2025 [March 22nd, 2025]
- Predicting HIV treatment nonadherence in adolescents with machine learning - News-Medical.Net - March 22nd, 2025 [March 22nd, 2025]
- AI And Machine Learning In Ink And Coatings Formulation - Ink World Magazine - March 22nd, 2025 [March 22nd, 2025]
- Counting whales by eavesdropping on their chatter, with help from machine learning - Mongabay.com - March 22nd, 2025 [March 22nd, 2025]
- Associate Professor - Artificial Intelligence and Machine Learning job with GALGOTIAS UNIVERSITY | 390348 - Times Higher Education - March 22nd, 2025 [March 22nd, 2025]
- Innovative Machine Learning Tool Reveals Secrets Of Marine Microbial Proteins - Evrim Aac - March 22nd, 2025 [March 22nd, 2025]
- Exploring the role of breastfeeding, antibiotics, and indoor environments in preschool children atopic dermatitis through machine learning and hygiene... - March 22nd, 2025 [March 22nd, 2025]
- Applying machine learning algorithms to explore the impact of combined noise and dust on hearing loss in occupationally exposed populations -... - March 22nd, 2025 [March 22nd, 2025]
- 'We want them to be the creators': Karlie Kloss' coding nonprofit offering free AI and machine learning workshop this weekend - KSDK.com - March 22nd, 2025 [March 22nd, 2025]
- New headset reads minds and uses AR, AI and machine learning to help people with locked-in-syndrome communicate with loved ones again - PC Gamer - March 22nd, 2025 [March 22nd, 2025]
- Enhancing cybersecurity through script development using machine and deep learning for advanced threat mitigation - Nature.com - March 11th, 2025 [March 11th, 2025]