3 Where is Machine Learning and Deep Learning being applied right now
Deep learning starts with artificial intelligence
Saying that AI is an artificial intelligence doesn’t really tell you anythingmeaningful, which is why so many discussions and disagreements arise over thisterm. Yes, you can argue that what occurs is artificial, not having come froma natural source. However, the intelligence part is, at best, ambiguous.People define intelligence in many different ways. However, you can say thatintelligence involves certain mental exercises composed of the followingactivities: * Learning: Having the ability to obtain and process new information. * Reasoning: Being able to manipulate information in various ways. * Understanding: Considering the result of information manipulation. * Grasping truths: Determining the validity of the manipulated information. * Seeing relationships: Divining how validated data interacts with other data. * Considering meanings: Applying truths to particular situations in a manner consistent with their relationship. * Separating fact from belief: Determining whether the data is adequately supported by provable sources that can be demonstrated to be consistently valid.The list could easily get quite long, but even this list is prone tointerpretation by anyone who accepts it as viable. As you can see from thelist, however, intelligence often follows a process that a computer system canmimic as part of a simulation: 1. Set a goal based on needs or wants. 2. Assess the value of any currently known information in support of the goal. 3. Gather additional information that could support the goal. 4. Manipulate the data such that it achieves a form consistent with existing information. 5. Define the relationships and truth values between existing and new information. 6. Determine whether the goal is achieved. 7. Modify the goal in light of the new data and its effect on the probability of success. 8. Repeat Steps 2 through 7 as needed until the goal is achieved (found true) or the possibilities for achieving it are exhausted (found false).Even though you can create algorithms and provide access to data in support ofthis process within a computer, a computer’s capability to achieveintelligence is severely limited. For example, a computer is incapable ofunderstanding anything because it relies on machine processes to manipulatedata using pure math in a strictly mechanical fashion. Likewise, computerscan’t easily separate truth from mistruth. In fact, no computer can fullyimplement any of the mental activities described on the intelligence list.When thinking about AI, you must consider the goals of the people whodeveloped it. The goal is to mimic human intelligence, not replicate it. Acomputer doesn’t truly think, but it gives the appearance of thinking.However, a computer only appears intelligent when it comes tological/mathematical thinking. Unlike humans, however, a computer has no wayto mimic intrapersonal or creative intelligence.
Moving from machine learning to deep learning
Deep learning is a subset of machine learning, as previously mentioned. Inboth cases, algorithms appear to learn by analyzing extremely large amounts ofdata (however, learning can occur even with tiny datasets in some cases).However, deep learning varies in the depth of its analysis and the kind ofautomation it provides. You can summarize the differences between machinelearning and deep learning like this: * A completely different paradigm: Machine learning is a set of many different techniques that enable a computer to learn from data and to use what it learns to provide an answer, often in the form of a prediction. Machine learning relies on different paradigms such as using statistical analysis, finding analogies in data, using logic, and working with symbols. Contrast the myriad techniques used by machine learning with the single technique used by deep learning, which mimics human brain functionality. It processes data using computing units, called neurons, arranged into ordered sections, called The technique at the foundation of deep learning is the neural network. * Flexible architectures: Machine learning solutions offer many knobs (adjustments) called hyperparameters that you tune to optimize algorithm learning from data. Deep learning solutions use hyperparameters, too, but they also use multiple user-configured layers (the user specifies number and type). In fact, depending on the resulting neural network, the number of layers can be quite large and form unique neural networks capable of specialized learning: Some can learn to recognize images, while others can detect and parse voice commands. The point is that the term deep is appropriate; it refers to the large number of layers potentially used for analysis. The architecture consists of the ensemble of different neurons and their arrangement in layers in a deep learning solution. * Autonomous feature definition: Machine learning solutions require human intervention to succeed. To process data correctly, analysts and scientists use a lot of their own knowledge to develop working algorithms. For instance, in a machine learning solution that determines the value of a house by relying on data containing the wall measures of different rooms, the machine learning algorithm won’t be able to calculate the surface of the house unless the analyst specifies how to calculate it beforehand. Creating the right information for a machine learning algorithm is called feature creation, which is a time-consuming activity. Deep learning doesn’t require humans to perform any feature-creation activity because, thanks to its many layers, it defines its own best features. That’s also why deep learning outperforms machine learning in otherwise very difficult tasks such as recognizing voice and images, understanding text, or beating a human champion at the Go game (the digital form of the board game in which you capture your opponent’s territory).You need to understand a number of issues with regard to deep learningsolutions, the most important of which is that the computer still doesn’tunderstand anything and isn’t aware of the solution it has provided. It simplyprovides a form of feedback loop and automation conjoined to produce desirableoutputs in less time than a human could manually produce precisely the sameresult by manipulating a machine learning solution.The second issue is that some benighted people have insisted that the deeplearning layers are hidden and not accessible to analysis. This isn’t thecase. Anything a computer can build is ultimately traceable by a human. Infact, the General Data Protection Regulation (GDPR) requires that humansperform such analysis. The requirement to perform this analysis iscontroversial, but current law says that someone must do it.The third issue is that self-adjustment goes only so far. Deep learningdoesn’t always ensure a reliable or correct result. In fact, deep learningsolutions can go horribly wrong. Even when the application code doesn’t gowrong, the devices used to support the deep learning can be problematic. Evenso, with these problems in mind, you can see deep learning used for a numberof extremely popular applications.
3. Where is Machine Learning and Deep Learning being applied right now?
The wiki article gives an overview of all the domains where machine learninghas been applied. These include: * Computer Vision: for applications like vehicle number plate identification and facial recognition. * Information Retrieval: for applications like search engines, both text search, and image search. * Marketing: for applications like automated email marketing, target identification * Medical Diagnosis: for applications like cancer identification, anomaly detection * Natural Language Processing: for applications like sentiment analysis, photo tagging * Online Advertising, etcThe image given above aptly summarizes the applications areas of machinelearning. Although it covers broader topic of machine intelligence as a whole.One prime example of a company using machine learning / deep learning isGoogle.In the above image, you can see how Google is applying machine learning in itsvarious products. Applications of Machine Learning/Deep Learning are endless,you just have to look at the right opportunity!
Using Deep Learning for Facial Recognition
Even with tricks like encoding, though, human software engineers have beenincapable of creating sufficiently fast and accurate processes for comparingtwo encoded faces and determining whether they are similar enough to be deemedthe same person.That’s because developers, being human beings, have no idea of how it is theyprocess raw images into sensible visual information; it’s their brains that dothat job, and the developer of their brains was evolution.So, the field of facial recognition and identification didn’t really take offuntil developers stopped trying to design the perfect matching algorithmthemselves, and instead embraced the then-brand new field of machine learningto evolve that algorithm all over again.That’s because to do trial and error, you have to be not only undertake a lotof trials, but you have to be able to judge which of those trials were errors.To achieve this, we need a labeled machine learning dataset: a curated andannotated collection of examples that can be used by a machine learning systemto provide trial-and-error feedback, and foster productive learning.(Source: Microsoft Azure Face Identification Demo)So, a facial recognition dataset might be a collection of photos of humanfaces — along with some photos of animal faces and face-like objects that arenot faces at all.Each of the photos in the dataset will be appended with metadata thatspecifies the real contents of the photo, and that metadata is used to(in)validate the guesses of a learning facial recognition algorithm.Compiling the datasets to be used by a machine learning system is often farmore time-consuming and expensive than actually using those datasets to trainthe system itself.There are a number of different algorithms used to turn the guesses of astill-learning facial recognition program into “learned” modifications to theprogram itself, but the most basic principle is that the program should repeatsuccesses and not mistakes.Correct guesses very slightly increase the likelihood that the approach thatled to the correct guess will be used again in future runs, while incorrectguesses slightly decrease the same.“Deep” learning is a more elaborate approach to this system of implementingtrial outcomes as processing changes, one that can find seemingly hidden,multi-step solutions.These deep learning solutions have brought facial recognition into the 21stcentury.Today, advanced facial recognition technology is working its way into crucialsecurity processes at banks, and the less-crucial ones in consumer mobilephones.When your phone unlocks because it recognized your face staring down at it,it’s using a basic approach to image analysis that was first invented via deeplearning.The market now uses a mixture of local facial recognition processes that runon a device itself and remote ones that require the sort of computinghorsepower that’s usually only available via the cloud.
Use of Statistics in Machine Learning
Let’s understand this. Suppose, I need to separate the mails in my inbox intotwo categories: ‘spam’ and ‘important’. For identifying the spam mails, I canuse a machine learning algorithm known as Naïve Bayes which will check thefrequency of the past spam mails to identify the new email as spam. NaïveBayes uses the statistical technique Baye’s theorem( commonly known asconditional probability). Hence, we can say machine learning algorithms usesstatistical concepts to execute machine learning.Additional Information: The main difference between machine learning andstatistical models come from the schools where they originated. While machinelearning originated from the department of computer science and statisticalmodelling came down from department of mathematics. Also any statisticalmodelling assumes a number of distributions while machine learning algorithmsare generally agnostic of the distribution of all attributes.
Machine Learning Applications in Social Media
Machine learning offers the most efficient means of engaging billions ofsocial media users. From personalizing news feed to rendering targeted ads,machine learning is the heart of all social media platforms for their own anduser benefits. Social media and chat applications have advanced to a greatextent that users do not pick up the phone or use email to communicate withbrands – they leave a comment on Facebook or Instagram expecting a speedyreply than the traditional channels.How Facebook uses Machine Learning ?VIDEOHere are some machine learning examples that you must be using and loving inyour social media accounts without knowing the fact that there interestingfeatures are machine learning applications – * Earlier Facebook used to prompt users to tag your friends but nowadays the social networks artificial neural networks machine learning algorithm identifies familiar faces from contact list. The ANN algorithm mimics the structure of human brain to power facial recognition. * The professional network LinkedIn knows where you should apply for your next job, whom you should connect with and how your skills stack up against your peers as you search for new job.These are just some of the most exciting machine learning examples reportedrecently using machine learning technology across diverse business domains,but we would love to hear of other machine learning applications if you’refamiliar with any. Share them in the comments below.Love what you just read? Well, don’t stop here, share it with you peers usingour social media icons on the left.Best difference between Machine learning and AIBoth Machine Learning and Artificial intelligence are absolute terms that aremaking a lot of buzz in the technology world. Both Ml and AI are completelydissimilar from each other in their logical thinking, algorithms, andapproach. Machine learning and Artificial intelligence both are components ofcomputer science that are compared with each other.Artificial intelligence and Machine learning are the most trendingtechnologies used for designing smart systems. Often many people, developers,and business owners get confused between Machine Learning and Artificialintelligence. to clear out that confusion we have differentiated both Machinelearning vs AI on a broad level.
Data used for Deep Learning
As everything is dependent on selecting the right data so that you can applydeep learning on various machine learning models, it mostly depends on theproblem you’re trying to solve.Deep learning can be applied to any data type. The data types you work with,and the data you gather, or any data you think of for the machine learningmodel to learn. Some of the data one can use are mentioned below. 1. Sound (Voice Recognition) 2. Text (Classifying Reviews) 3. Images (Computer Vision) 4. Time Series (Sensor Data, Web Activity) 5. Video (Motion Detection)
Deep Learning Interview Questions
Here are the basic 20 Deep Learning Interview questions that can help youduring the interview. Read the full article. Hope it will help you.
Machine Learning and Deep Learning
* * *Artificial Intelligence is one of the most popular trends of recent times.Machine learning and deep learning constitute artificial intelligence. TheVenn diagram shown below explains the relationship of machine learning anddeep learning −
Deep learning is a subfield of machine learning where concerned algorithms areinspired by the structure and function of the brain called artificial neuralnetworks.All the value today of deep learning is through supervised learning orlearning from labelled data and algorithms.Each algorithm in deep learning goes through the same process. It includes ahierarchy of nonlinear transformation of input that can be used to generate astatistical model as output.Consider the following steps that define the Machine Learning process * Identifies relevant data sets and prepares them for analysis. * Chooses the type of algorithm to use * Builds an analytical model based on the algorithm used. * Trains the model on test data sets, revising it as needed. * Runs the model to generate test scores.
Applications of Machine Learning and Deep Learning
In this section, we will learn about the different applications of MachineLearning and Deep Learning. * Computer vision which is used for facial recognition and attendance mark through fingerprints or vehicle identification through number plate. * Information Retrieval from search engines like text search for image search. * Automated email marketing with specified target identification. * Medical diagnosis of cancer tumors or anomaly identification of any chronic disease. * Natural language processing for applications like photo tagging. The best example to explain this scenario is used in Facebook. * Online Advertising.
Deep Learning Algorithms
We could define deep learning as a class of machine learning techniques whereinformation is processed in hierarchical layers to understand representationsand features from data in increasing levels of complexity. In practice, alldeep learning algorithms are neural networks, which share some common basicproperties. They all consist of interconnected neurons that are organized inlayers. Where they differ is network architecture (the way neurons areorganized in the network), and sometimes the way they are trained.With that in mind, let’s look at the main classes of neural networks. Thefollowing list is not exhaustive, but it represents the vast majority ofalgorithms in use today.
Convolutional Neural Networks (CNNs)
A CNN is a feedforward neural network with several types of special layers.For example, convolutional layers apply a filter to the input image (or sound)by sliding that filter all across the incoming signal, to produce ann-dimensional activation map. There is some evidence that neurons in CNNs areorganized similarly to how biological cells are organized in the visual cortexof the brain. Today, they outperform all other ML algorithms on a large numberof computer vision and natural language processing tasks.