Skip to main content

Machine Learning - A World where Machines are Learning to Become Humans

We all love to surf the Internet, go through applications to explore new technology. We like to indulge ourselves in things that takes us least of time, or that makes our tasks a lot easier. As the younger generation we take a keen interest in making ourselves upto-date with the upcoming advancements. But how many of us have wondered what goes on in behind-the-scenes of these recent upcoming machinery?

Well, it's the new technology known as Machine Learning, that is governing the industrial world since it's advent. And it's starting to gain its momentum ever since. It's my first blog here that will brief you through this new-born technology, and the way it's shaping our world without you realizing about it.

So readers, gear yourself up for the journey that unfolds!

Machine Learning: A Brief Introduction

Machine learning (ML) is the scientific study of algorithms and statistical models that computer systems use to progressively improve their performance on a specific task. Machine learning algorithms build a mathematical model of sample data, known as 'training data', in order to make predictions or decisions without being explicitly programmed to perform the task.

For instance, you are going through your YouTube or Instagram feed. You find stuff that is relevant to your previous search, or the type of stuff frequently visited or followed by you. The applied mechanism makes a note of your behavior, your likes and your frequently visited posts. This is used to memorise to give a more user-friendly environment. It makes the handling more interactive.


So basically, ML is used to make machines learn things on its own, without the programmer's intervention to program to learn for each and every task. That sounds interesting!  

What does Machine Learning consist of?

The Machine Learning algorithms are often categorised as Supervised and Unsupervised
  • Supervised machine learning algorithms can apply what has been learned in the past to new data using labeled examples to predict future events. Starting from the analysis of a known training dataset, the learning algorithm produces an inferred function to make 'predictions' about the output values. The system is able to provide targets for any new input after sufficient training.
    • In contrast, unsupervised machine learning algorithms are used when the information used to train is neither classified nor labeled. The system doesn’t figure out the right output, but it explores the data and can draw inferences from datasets to describe hidden structures from unlabeled data.
    • Reinforcement machine learning algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards. Trial and error search and delayed reward are the most relevant characteristics of reinforcement learning. This method allows machines and software agents to automatically determine the ideal behavior within a specific context in order to maximize its performance. Simple reward feedback is required for the agent to learn which action is best; this is known as the reinforcement signal.

    What is an Artificial Neural Network?

    An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain processes information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurones) working in unison to solve specific problems.

    ANNs, just like any person, learns by example and experience. An ANN is configured for a specific application, such as pattern recognition or data classification, through a learning process. Learning in biological systems involves adjustments to the synaptic connections that exist between the neurones. This is true for ANNs as well.

    Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques.

    The various applications include - Adaptive learning, Self-Organisation, Real Time Operation, and many more.

    What does Deep Learning mean? 

    While going through various articles over the Internet, you might come across the term Deep Learning. So what is deep learning?

    Deep Learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks. It is a Large Neural Networks. The "deep" in "deep learning" refers to the number of layers through which the data is transformed. In deep learning, each level learns to transform its input data into a slightly more abstract and composite representation.

    Most modern deep learning models are based on an artificial neural network, although they can also include propositional formulas or latent variables organized layer-wise in deep generative models such as the nodes in deep belief networks and deep Boltzmann machines.

    You must be thinking about Artificial Intelligence (AI), as well! And what makes Artificial Intelligence different from Machine Learning. Machine Learning and Artificial Intelligence are not mutually exclusive. But there exists quite a difference between the two.

    Artificial Intelligence vs. Machine Learning

    People tend to use these terms interchangeable, especially in the world of big data. Both the fields have different applications.

    Artificial intelligence is a broader concept than machine learning, which addresses the use of computers to mimic the cognitive functions of humans. When machines carry out tasks based on algorithms in an “intelligent” manner, that is AI. Machine learning is a subset of AI and focuses on the ability of machines to receive a set of data and learn for themselves, changing algorithms as they learn more about the information they are processing.

    Applications of ML in our day-to-day life

    Artificial Intelligence is every where. Possibly you are using it in one way or the other, without knowing it.

    • Virtual Personal Assistance

    Siri, Cortana, and Google Now are some of the virtual personal assistants that guide you through your work, when asked over voice. You can go with 'Siri, How is the weather today?', 'Cortana, find the nearest shop by me.', or simply 'What do I do today?'.

    Machine learning is an important part of these personal assistants as they collect and refine the information on the basis of your previous involvement with them. These are programmed to look through your personal information stored in its database, recalls your call related queries, or invokes other apps on its own to perform the mentioned task.

    • Social Media

    'People You May Know' suggestions. Facebook continuously learns from who your friends are, the interests you share likes, or frequently visited pages, posts, etcetera. According to your experience with it, it suggests you a list of people that you may know, or you can become friends with.

    'Similar Pins'. Pinterest uses this ML technology to recommend you pins that might be of your interest, by 'learning' your behavior.

    • E-mail spam and Malware filtering.

    The various spam filtering approaches are applied to emails, with the very help of Machine Learning. These spam filtering techniques are timely updated to get past the new tricks applied by spammers.
    Multi Layer Perceptron, C 4.5 Decision Tree Induction are some of the spam filtering techniques that are powered by ML.

    • Search Engine Result Refining

    Search engines like Google use machine learning to improve the search results for you. Every time you execute a search, the algorithms at the backend keep a watch at how you respond to the results.  If you open the top results and stay on the web page for long, the search engine assumes that the the results it displayed were in accordance to the query.

    In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome.

    Careers in Machine Learning

    Students learning Machine Learning will have a wide array of opportunities ahead of them, as the society edges closer to automating a number of processes which are done today by human beings. The scope is increasing day by day because the industries today need more and more algorithms. Following are the career options in Machine Learning.

    • Data Scientist
    Data scientists are required to source voluminous sets of data located in disparate places to find actionable insights, information on which action can be taken. This job also entails looking for problems and working to correct these issues.

    The position of data scientist incorporates machine learning, and he or she will be occupied with finding meaning in the data. A data scientist will attempt to understand the deeper implications and human impact of her project and will work with others, collaborating with those in divergent disciplines to arrive at the answers that she needs.

    • Software Engineer
    The job of a software engineer will require a strong aptitude for writing code, as the candidate will be tasked with creating code that supports the development of algorithms. As such, the software engineer will need to write a program that details how the computer is to perform specific functions, and this must be written using step-to-step instructions. The software engineer must be able to convert programs into executable files, and after undergoing rigorous testing, he should be able to fix bugs, if there are any. 

    • Computational Linguist

    The technologies of machine learning often work in tandem with voice-recognition software to help people navigate through telephone systems for banks, utility companies, and doctors’ offices. Computer linguists help computers learn how to understand spoken language and to continually improve the systems that currently exist. Talk to text applications are becoming more popular and are also a tool for people who are blind.

    Computational linguists also help computers learn patterns of speech, and they can help computers acquire the capability for translating words into other spoken languages. The goal, in many cases, is to help the machines actually comprehend language.

    Machine Learning: The Present and the Future

    Machine Learning is defining our present, and it will continue to play a significant role in our lives in the near future. We will be defined by the machines we have working around us.
    • Connie
    A Watson-enabled robot concierge, has made its debut at the Hilton McLean. IBM has developed the robot, which draws on domain knowledge from Watson and WayBlazer to help hotel guests figure out what to visit, where to dine, and how to find anything at the property. Connie is named for Hilton Worldwide’s founder Conrad Hilton.
    Source

    • Sophia Hanson - The world's first robot celebrity

    Sophia is a social humanoid robot developed by Hong Kong based company Hanson Robotics. Sophia was activated on February 14, 2016 and made her first public appearance at South by Southwest Festival (SXSW) in mid-March 2016 in Austin, Texas, United States. It is able to display more than 50 facial expressions.

    Sophia has been covered by media around the globe and has participated in many high-profile interviews. In October 2017, Sophia became the first robot to receive citizenship of any country. In November 2017, Sophia was named the United Nations Development Programme's first ever Innovation Champion, and is the first non-human to be given any United Nations title.
    Source: Wikipedia.

    • Bomb Squad
    There are more than 450 bomb squads in America, which respond to thousands of bomb-related incidents each year, according to federal statistics. Already, some of these bomb squads use robots, which often can better dispose of the bombs, while minimizing the risk to human lives.

    A wheeled robot with various sensors from the Union County bomb squad checks a simulated suspect vehicle during a terrorism-response exercise coordinated by the Department of Homeland Security at Kean College in Hillside, N.J. Source

    • Stockroom Workers
    In Amazon warehouses, many of your packages may have been handled not by people, but by robots. Indeed, from the 2015 to the 2016 holiday seasons, Amazon upped its fleet of robots by 50% to roughly 45,000 robots in 20 fulfillment centers. This robot army makes Amazon’s operations more efficient.

    • Flying Smarter: AI & Machine Learning in Aviation Autopilot Systems

    The Conclusion:

    With such fast-paced advancements, the day is not far when we would be able to witness machines doing the tasks done by people now. Machines behaving like our fellow beings, assisting us in our day-to-day activities, helping us in business, carrying out complex calculations, or maybe doing stuff that is not possible for humans to perform. Soon, we would be observing life-like robots that can keep you company, like a real human being.

    The future predicted in many Hollywood movies and the science-fiction films, like Transformers, The Terminator, could come real; or maybe our cute Marvel robot Baymax would be working among us!

    Hope this blog of mine was quite informative to introduce you to the world of Machines, and the realm of technologies like Machine Learning and Artificial Intelligence.
    Happy Reading!

    (Source: Internet.   Pic Courtesy: Google.  Video Courtesy: YouTube)

    Comments

    Post a Comment

    Popular posts from this blog

    A Dive into Representational Learning and Generative Models with Autoencoders and GANs

    In the ever-evolving landscape of artificial intelligence, the quest for machines to understand and generate meaningful representations of data has led to remarkable breakthroughs. Representational learning , a subfield of machine learning, explores the intricate process of learning hierarchical and abstract features from raw data. Two powerful techniques that have gained significant traction in this domain are Autoencoders and Generative Adversarial Networks (GANs).  Figure 1. Generative Adversarial Network In this blog post, we will embark on a journey to explore the fascinating world of representational learning and generative models, delving into the mechanics of Autoencoders and GANs. The Jupyter Notebook for this blog can be found here . Table of Contents: Autoencoders: Unveiling Latent Representations Efficient Data Representations Performing PCA with an Undercomplete Linear Autoencoder Stacked Autoencoders Implementing a Stacked Autoencoder Using Keras Visualizing the Reco...
    Post a Comment
    Read more

    Reinforcement Learning: A Journey into Intelligent Decision-Making

    In the ever-evolving landscape of artificial intelligence, Reinforcement Learning (RL) has emerged as a powerful paradigm, enabling machines to learn and make decisions through interaction with their environment. Let's dive into the world of reinforcement learning without further ado. Imagine training a dog named Max using treats as positive reinforcement. When Max successfully follows a command like "sit" or "stay", the owner immediately rewards him with a tasty treat. The positive association between the action and the treat encourages Max to repeat the desired behavior. Over time, Max learns to associate the specific command with the positive outcome of receiving a treat, reinforcing the training process. Figure 1. A simple example of Reinforcement Learning Table of Contents: Understanding Reinforcement Learning Key components of RL Exploring applications of RL Policy Search Neural Network Policies Types of Neural Network Policies Evaluating Actions: The Cre...
    Post a Comment
    Read more

    Transformative Tales: Unleashing the Power of Natural Language Processing with RNNs and Attention Mechanisms

    In the ever-evolving landscape of artificial intelligence, Natural Language Processing (NLP) has emerged as a captivating frontier, revolutionizing how machines comprehend and interact with human language. Among the many tools in the NLP arsenal, Recurrent Neural Networks (RNNs) and attention mechanisms stand out as key players, empowering models to understand context, capture nuances, and deliver more sophisticated language processing capabilities.  Let's embark on a journey into the world of NLP, where the synergy of RNNs and attention mechanisms is reshaping the way machines interpret and generate human-like text. Figure 1. An RNN unrolled through time The Jupyter Notebook for this blog can be found  here . Table of Contents: What is Natural Language Processing (NLP)? Generative Shakespearean Text Using a Character RNN Creating the Training Dataset How to Split a Sequential Dataset Chopping the Sequential Dataset into Multiple Windows Building and Training the Char-RNN Mode...
    Post a Comment
    Read more