Machine Learning for dummies
Machine learning is an application of artificial intelligence which refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term may also be applied to any machine that exhibits traits associated with a human mind such as learning and problem-solving.
What is Machine Learning?
SIMPLY put Machine Learning is the science of getting computers to learn and act like humans do, and improve their learning over time in autonomous fashion, by feeding them data and information in the form of observations and real-world interactions.
This shows the ideal objective or ultimate aim of machine learning, which may make a lot of people confused between Artificial intelligence and Machine Learning however, there are some distinct differences readers should recognize as well.
How Machine Learning is different from Artificial intelligence?
Machine learning is just one method for achieving artificial intelligence. At the birth of the idea of Artificial intelligence in the 1950s, AI was defined as any machine capable of performing a task that would normally require human intelligence. AI systems will generally demonstrate at least some of the following traits: planning, learning, reasoning, problem-solving, perception, motion, and manipulation and, to maybe have social intelligence and creativity.
A brief history about machine learning
The history of Machine Learning, like many other artificial intelligence stories, began with seemingly promising works in the 1950s and 1960s, followed by a long period of accumulation of knowledge known as the winter of artificial intelligence. The first pioneers of Machine Learning were Arthur Samuel, Joseph Weizbaum and Frank Rosenblatt. The first was widely known for the creation in 1952 of the self-learning Checkers-playing program, which, as its name suggests, was able to play checkers. Perhaps more significant for the descendants was his participation with Donald Knut in the TeX project, the result of which was a system of computer layout, which has been unrivaled for almost 40 years for the preparation of mathematical texts. The second in 1966 wrote a virtual interlocutor ELIZA, able to imitate (or rather parody) the dialogue with a psychotherapist, obviously, that the name of the program owes to the heroine from the play by Bernard Shaw. And then Rosenblatt went on to build the Mark I Perceptron system at Cornell University in the late 50s, which can be recognized as the first neurocomputer. and from there the new era of machine learning started.
A few concepts about machine learning
The core benefit of machine learning is that it can predict based on patterns fed to the machine through data. For example If you’re just tagging your friend’s faces in pictures, you’re not using a machine learning model. If you upload a new photo and suddenly it tells you who each person is, then you’re looking at some king of machine learning algorithm. The whole point of machine learning is to predict things based on patterns and other factors it has been trained with.
Machine learning requires training
You have to tell a machine learning model what its trying to predict. Think about how a human child learns. The first time they see a banana, they have no idea what it is. You then tell them it is a banana. The next time they see one they’ll identify it as a banana. Machine learning works in a similar way. You show it as many pictures of a banana as you possibly can, tell it its a banana, and then test it with a picture of a banana it wasn’t trained on.
What are algorithms and how they are the core of machine learning
simply put according to Wikipedia algorithms are step-by-step procedure for calculations.
Rather than follow only explicitly programmed instructions, some computer algorithms are designed to allow computers to learn on their own (i.e., facilitate machine learning). Uses for machine learning include data mining and pattern recognition. These mathematical creations determine what you see in your Facebook feed, what movies Netflix recommends to you, and what ads you see in your Gmail.
Types of Machine Learning & Common Algorithms
Machine learning is not an exact science. It encompasses a broad range of machine learning tools, techniques, and ideas. Here are the most common types of machine learning techniques and algorithms along with a brief summary of how each can be used to solve problems.
Supervised learning
Supervised learning is a process like you are learning under someone’s else supervision. In supervised learning, the process of an algorithm learning from the training datasets can be thought of as a teacher supervising the learning process. The correct answers are known, the algorithm then makes predictions on the training data and its been corrected by the teacher. The learning phase continues to progress until the algorithm achieves an acceptable level of accuracy. In supervised learning, data is given with its associated labels. learn more about Supervised learning from here.
Unsupervised learning
Unsupervised learning is where you only have input data (X) and no corresponding output variables. The goal for unsupervised learning is to model the underlying structure or distribution in the data in order to learn more about the data. These are called unsupervised learning because unlike supervised learning above there is no correct answers and there is no teacher. Algorithms are left to their own devises to discover and present the interesting structure in the data. Unsupervised learning problems can be further grouped into clustering and association problems. learn more about Supervised learning from here.
Reinforcement learning
Reinforcement learning is learning by interacting with an environment. The machine learns from the consequences of its actions, rather than from being explicitly taught and it selects its actions on basis of its past experiences (exploitation) and also by new choices (exploration), which is essentially trial and error learning. The reinforcement signal that the machine receives is a numerical reward, which encodes the success of an action’s outcome, and the agent seeks to learn to select actions that maximize the accumulated rewards over time. learn more about Supervised learning from here.
Semi-supervised learning
Semi-supervised learning is supervised learning where the training data contains very few labeled examples and a large number of unlabeled examples.
The goal of a semi-supervised learning model is to make effective use of all of the available data, not just the labelled data like in supervised learning.
It is common for many real-world supervised learning problems to be examples of semi-supervised learning problems given the expense or computational cost for labeling examples. For example, classifying photographs requires a datasets of photographs that have already been labeled by human operators.
Many problems from the fields of computer vision (image data), natural language processing (text data), and automatic speech recognition (audio data) fall into this category and cannot be easily addressed using standard supervised learning methods. learn more about Supervised learning from here.
what are datasets
Any named group of records is called a data set. Data sets can hold information such as medical records or insurance records, to be used by a program running on the system. Data sets are also used to store information needed by applications or the operating system itself, such as source programs.
In simplest terms, a record is a fixed number of bytes containing data. Often, a record collects related information that is treated as a unit, such as one item in a database or personnel data about one member of a department.
Datasets are used in machines learning to train on, and they are an important part of machine learning it could be as important as the algorithm itself, what makes a successful machine learning agent and a bad one could be simply the data set that it was trained on. read this to learn more about datasets.
Applications of Machine Learning
After learning some basic function of machine learning lets see what kind of applications it can be used in:
Data Security: Malware is a problem that isn’t going to go away anytime soon. The bad news is that thousands of new malware variants are detected every day. The good news is that new malware almost always has the same code as previous versions. This means that machine learning can be used to look for patterns and report anomalies.
Financial Trading: Patterns and predictions are what keeps the stock market alive. Machine learning algorithms are in use by some of the world’s biggest trading companies to predict and execute transactions at high volume and high speed.
Marketing and commerce: When you understand your customers, you can serve them better. When you serve them better, you sell more. Marketing companies uses machine learning algorithms to create a truly personalized customer experience that is matched to their previous behavior, likes and dislikes, and location-based data, such as where they prefer to shop.
Healthcare Industry: Machine learning in healthcare is one of the most growing industries in the medical industry. Google recently developed a machine-learning algorithm to identify cancerous tumors in mammograms, and researchers at Stanford University are using deep learning to identify skin cancer. Machine Learning is already lending a hand in diverse situations in healthcare. machine learning in healthcare helps to analyze thousands of different data points and suggest the most accurate outcomes, provide small risk scores, precise resource allocation, and has many other applications. read more about google’s attempts to bring machine learning to the healthcare industry here.
Retail Industry: Businesses organizations that are in the retail industry or e-commerce companies have been using advanced machine learning applications including Recommendation systems, Chat-bot applications, Predictive Analytics systems, etc. to innovate and enhance their business processes. A number of big Retail and E-commerce industries like Walmart, Amazon, Alibaba have successfully incorporated AI and Machine Learning technologies across their entire sales cycles from logistics to sales to post-sales services, thus improve results as well as business processes.
a side from these few fields that uses machine learning there are much more that are being introduced to machine learning every day.
