Machine Learning
Updated: Nov 25
Machine Learning is a branch of Artificial Intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention. It uses data and algorithms to mimic how humans learn, gradually improving its accuracy. It allows computers to learn without being explicitly programmed. It gives enterprises a view of trends in customer behavior and business operational patterns, as well as supports the development of new products. Many of today's leading companies use machine learning as a central part of their operations. Machine learning has become a significant competitive differentiator for many companies.
How Machine Learning Works
The 3 components of Machine Learning:
Decision Processes: Machine Learning algorithms perform predictions or classifications based on labeled or unlabeled input data. An algorithm will estimate a pattern in the data.
Error Function: Evaluates the prediction of the model. Used to assess the accuracy of a model by comparison if there are known examples.
Optimization Process: When the model fits better to the data points in the training set, the weights are adjusted to minimize the difference between the known example and the model estimate. The algorithm will keep repeating this evaluation and optimizing the process and updating weights autonomously until a threshold of accuracy is achieved.
In Simple Terms:
A computational algorithm is at the core of making decisions.
Variables and features that make up the decision.
Base knowledge for which the answer is known enables (trains) the system to learn.
Initially, a model is fed parameter data with a known answer. After running the algorithm, adjustments are made until the output (learning) agrees with the known answer. This is when the system begins to learn and take higher computational decisions with the help of increasing amounts of data.
Machine Learning Is Used In
Internet search engines
Email filters to sort out spam
Websites to make personalized recommendations
Banking software to detect unusual transactions
Chatbots
Manufacturing: Predictive maintenance and condition monitoring
Retail: Upselling and cross-channel marketing
Healthcare and life sciences: Disease identification and risk satisfaction
Travel and hospitality: Dynamic pricing
Financial Services: Risk analytics and regulation
Energy: Energy demand and supply optimization
Image recognition:
It can identify an object as a digital image, based on the intensity of the pixels in images.
Real-world examples of image recognition:
i. Label an x-ray as cancerous or not.
ii. Assign a name to a photographed face (tagging on social media).
iii. Recognize handwriting by segmenting a single letter into smaller images.
Speech recognition:
The speech can be segmented on the basis of intensity levels on time-frequency bands. Machine learning can translate speech into text. Specific software applications can convert live voice and recorded speech into a text file.
Real-world examples of speech recognition:
i. Voice Search
ii. Voice Dialing
iii. Appliance Control
All businesses rely on data to function. The ability to make data-driven decisions increasingly determines whether companies stay ahead of their competitors or fall further behind. Machine learning can be the key to leveraging corporate and customer data and making competitive decisions.