Two generation on Machine Learning: Grandpa and me!
Last time I was on a visit to my grandparents house I had a an interesting exchange with grandpa on future , how each one of us sees it and he asked the question “are we in the era of self driven cars yet ??”
Answering his question I included a handful of technical jargon however the gasp came when I mentioned “Machine Learning” so here’s what happened:
Actually machine learning is not a bright new term since in 1959 MIT engineer and an artificial intelligence pioneer Arthur Samuel described machine learning as a “Field of study that gives computers the ability to learn without being explicitly programmed.”
Recently, the advent of the internet presented a trove of accumulated data. With so much information readily available, there seemed but one thing to do: figure out a way to organize it into meaningful patterns — one of machine learning’s most integral roles.
But how? why?
A.I. and machine learning are often conflated, but they’re not the same thing. Artificial intelligence refers to a machine’s ability to perform intelligent tasks, whereas machine learning refers to the automated process by which machines weed out meaningful patterns in data. Without machine learning, artificial intelligence as we know it wouldn’t be possible.
ML is a subset of artificial intelligence; in fact, it’s simply a technique for realizing AI.
Furthermore Machine Learning is not the new automation:
To automate flows rules act in the same manner every time but machine learning helps machines learn by past data and change their decisions/performance accordingly. Spam detection in our mailboxes is driven by machine learning. Hence, it continues to evolve with time.
“The only relation between the two things is that machine learning enables better automation”
Clearing out the misconceptions about M.L we can now dive now in detailed explanation of our subject.
M.L(Machine Learning)
Each scientist or field expert may give you its own definition to machine learning but for me these are the most potent approaches:
“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 definition draws the perfect complete image of M.L and its greatest aim.
“Machine learning follows a process of preparing data, training an algorithm and generating a machine learning model, and then making and refining predictions.”
— -> 4 key successive words: data — algorithm — model — predictions
Methods:
n machine learning, tasks are generally classified into broad categories. These categories are based on how learning is received or how feedback on the learning is given to the system developed.
Two of the most widely adopted machine learning methods are supervised learning which trains algorithms based on example input and output data that is labeled by humans, and unsupervised learning which provides the algorithm with no labeled data in order to allow it to find structure within its input data.
Supervised machine learning
Supervised machine learning uses sample data that is well classified and labeled. It’s supervised because it involves a set of feedback data that indicates whether the predictions based on the sample data are correct or incorrect.
The purpose of this method is for the algorithm to be able to “learn” by comparing its actual output with the “taught” outputs to find errors, and modify the model accordingly.
A common use case of supervised learning is to use historical data to predict statistically likely future events. It may use historical stock market information to anticipate upcoming fluctuations, or be employed to filter out spam emails. In supervised learning, tagged photos of dogs can be used as input data to classify non tagged photos of dogs.
Unsupervised machine learning
Unsupervised machine learning uses unlabeled data, usually in large amounts. Think of social media applications like Twitter or Instagram that generate vast amounts of unlabeled, unstructured data. Unsupervised learning algorithms can help gain meaningful information from this type of data by classifying it based on patterns or clusters. There is no feedback data to indicate whether classifications are correct or incorrect because the objective is to develop the classifications based on structures hidden in the data.
The goal of unsupervised learning may be as straightforward as discovering hidden patterns within a data set, but it may also have a goal of feature learning, which allows the computational machine to automatically discover the representations that are needed to classify raw data.
Unsupervised learning is commonly used for transactional data. You may have a large data set of customers and their purchases, but as a human you will likely not be able to make sense of what similar attributes can be drawn from customer profiles and their types of purchases. With this data fed into an unsupervised learning algorithm, it may be determined that women of a certain age range who buy unscented soaps are likely to be pregnant, and therefore a marketing campaign related to pregnancy and baby products can be targeted to this audience in order to increase their number of purchases.
Without being told a “correct” answer, unsupervised learning methods can look at complex data that is more expansive and seemingly unrelated in order to organize it in potentially meaningful ways. Unsupervised learning is often used for anomaly detection including for fraudulent credit card purchases, and recommender systems that recommend what products to buy next. In unsupervised learning, untagged photos of dogs can be used as input data for the algorithm to find likenesses and classify dog photos together.
Reinforcement machine learning
As compared to unsupervised learning, reinforcement learning is different in terms of goals. While the goal in unsupervised learning is to find similarities and differences between data points, in reinforcement learning the goal is to find a suitable action model that would maximize the total cumulative reward of the agent.
For example, in usual circumstances we would require an autonomous vehicle to put safety first, minimize ride time, reduce pollution, offer passengers comfort and obey the rules of law. With an autonomous race car, on the other hand, we would emphasize speed much more than the driver’s comfort. The programmer cannot predict everything that could happen on the road. Instead of building lengthy “if-then” instructions, the programmer prepares the reinforcement learning agent to be capable of learning from the system of rewards and penalties. The agent (another name for reinforcement learning algorithms performing the task) gets rewards for reaching specific goals.
Deep Neural Networks
Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. They interpret sensory data through a kind of machine perception, labeling or clustering raw input.
To get a feel for how neural networks work, imagine you wanted to build an algorithm to detect whether an image contained a human face. A basic deep neural network would have several layers of thousands of neurons each. In the first layer, each neuron might learn to look for one basic shape, like a curve or a line. In the second layer, each neuron would look at the first layer, and learn to see whether the lines and curves it detects ever make up more advanced shapes, like a corner or a circle. In the third layer, neurons would look for even more advanced patterns, like a dark circle inside a white circle, as happens in the human eye. In the final layer, each neuron would learn to look for still more advanced shapes, such as two eyes and a nose. Based on what the neurons in the final layer say, the algorithm will then estimate how likely it is that an image contains a face.
The magic of deep learning is that the algorithm learns to do all this on its own. The only thing a researcher does is feed the algorithm a bunch of images and specify a few key parameters, like how many layers to use and how many neurons should be in each layer, and the algorithm does the rest.
I hope you’re still with me grandpa you’re not loaded yet right?
So If you want we went through several methods of M.L that can be all thought of different ways of teaching machine the same way as you and me didn’t get the same education.
ML evolved throughout time to reach its ultimate goal which I think “to craet the smartest machine” the machine which conducts the fastest and brightest deduction.
“Aren’t you feeling threatened?”
I know the contribution of ML is vast and will likely surpass Humans and cut out millions of jobs but it is Human-dependant and “founded” essentially to help not the contrary so humans are constantly revising whether it is driven away so we ‘re cautiously examining the procedure as it goes and ML has helped more than caused harm ther’s why we’re still working on it to enhace it so it thinks objectively and disinterestedly.
References:
https://www.ibm.com/topics/machine-learning
https://www.brookings.edu/research/what-is-machine-learning/
