How to explain machine learning in plain English

The term “machine learning” was coined by Arthur Samuel, a computer scientist at IBM and a pioneer in AI and computer gaming. The more the program played, the more it learned from experience, using algorithms to make predictions. Siri was created by Apple and makes use of voice technology to perform certain actions. When we fit a hypothesis algorithm for maximum possible simplicity, it might have less error for the training data, but might have more significant error while processing new data.

An ML model is a mathematical representation of a set of data that can be used to make predictions or decisions. Once the model is trained, it can be used to make predictions or decisions on new data. Until the 80s and early 90s, machine learning and artificial intelligence had been almost one in the same. But around the early 90s, researchers began to find new, more practical applications for the problem solving techniques they’d created working toward AI. A Bayesian network is a graphical model of variables and their dependencies on one another.

The current incentives for companies to be ethical are the negative repercussions of an unethical AI system on the bottom line. To fill the gap, ethical frameworks have emerged as part of a collaboration between ethicists and researchers to govern the construction and distribution of AI models within society. Some research (link resides outside ibm.com) shows that the combination of distributed responsibility and a lack of foresight into potential consequences aren’t conducive to preventing harm to society. The program plots representations of each class in the multidimensional space and identifies a “hyperplane” or boundary which separates each class. When a new input is analyzed, its output will fall on one side of this hyperplane.

Since 2015, Trend Micro has topped the AV Comparatives’ Mobile Security Reviews. The machine learning initiatives in MARS are also behind Trend Micro’s mobile public benchmarking continuously being at a 100 percent detection rate — with zero false warnings — in AV-TEST’s product review and certification reports in 2017. Trend Micro’s Script Analyzer, part of the Deep Discovery™ solution, uses a combination of machine learning and sandbox technologies to identify webpages that use exploits in drive-by downloads. The emergence of ransomware has brought machine learning into the spotlight, given its capability to detect ransomware attacks at time zero. Signals travel from the first (input), to the last (output) layer, possibly after traversing the layers multiple times. In terms of purpose, machine learning is not an end or a solution in and of itself.

If you choose machine learning, you have the option to train your model on many different classifiers. You may also know which features to extract that will produce the best results. Plus, you also have the flexibility to choose a combination of approaches, use different classifiers and features to see which arrangement works best for your data. For example, if a cell phone company wants to optimize the locations where they build cell phone towers, they can use machine learning to estimate the number of clusters of people relying on their towers.

For the sake of simplicity, we have considered only two parameters to approach a machine learning problem here that is the colour and alcohol percentage. But in reality, you will have to consider hundreds of parameters and a broad set of learning data to solve a machine learning problem. Good quality data is fed to the machines, and different algorithms are used to build ML models to train the machines on this data. The choice of algorithm depends on the type of data at hand and the type of activity that needs to be automated. Once the model is trained, it can be evaluated on the test dataset to determine its accuracy and performance using different techniques. Like classification report, F1 score, precision, recall, ROC Curve, Mean Square error, absolute error, etc.

It’s not just about technology; it’s about reshaping how computers interact with us and understand the world around them. As artificial intelligence continues to evolve, machine learning remains at its core, revolutionizing our relationship with technology and paving the way for a more connected future. Machine learning starts with data — numbers, photos, or text, like bank transactions, pictures of people https://chat.openai.com/ or even bakery items, repair records, time series data from sensors, or sales reports. The data is gathered and prepared to be used as training data, or the information the machine learning model will be trained on. When companies today deploy artificial intelligence programs, they are most likely using machine learning — so much so that the terms are often used interchangeably, and sometimes ambiguously.

Top 20 Generative AI Applications/ Use Cases Across Industries

Just connect your data and use one of the pre-trained machine learning models to start analyzing it. You can even build your own no-code machine learning models in a few simple steps, and integrate them with the apps you use every day, like Zendesk, Google Sheets and more. Fueled by advances in statistics and computer science, as well as better datasets and the growth of neural networks, machine learning has truly taken off in recent years.

Despite their similarities, data mining and machine learning are two different things. Both fall under the realm of data science and are often used interchangeably, but the difference lies in the details — and each one’s use of data. The world of cybersecurity benefits from the marriage of machine learning and big data. Both machine learning techniques are geared towards noise cancellation, which reduces false positives at different layers. Learning rates that are too high may result in unstable training processes or the learning of a suboptimal set of weights. Learning rates that are too small may produce a lengthy training process that has the potential to get stuck.

If the data are bad to learn, such as non-representative, poor-quality, irrelevant features, or insufficient quantity for training, then the machine learning models may become useless or will produce lower accuracy. Therefore, effectively processing the data and handling the diverse learning algorithms are important, for a machine learning-based solution and eventually building intelligent applications. In machine learning and data science, high-dimensional data processing is a challenging task for both researchers and application developers. Thus, dimensionality reduction which is an unsupervised learning technique, is important because it leads to better human interpretations, lower computational costs, and avoids overfitting and redundancy by simplifying models.

This global threat intelligence is critical to machine learning in cybersecurity solutions. Machine learning algorithms are able to make accurate predictions based on previous experience with malicious programs and file-based threats. By analyzing millions of different types of known cyber risks, machine learning is able to identify brand-new or unclassified attacks that share similarities with known ones. These techniques include learning rate decay, transfer learning, training from scratch and dropout. Initially, the computer program might be provided with training data — a set of images for which a human has labeled each image dog or not dog with metatags. The program uses the information it receives from the training data to create a feature set for dog and build a predictive model.

Machine Learning (ML) Models

Use supervised learning if you have known data for the output you are trying to predict. An open-source Python library developed by Google for internal use and then released under an open license, with tons of resources, tutorials, and tools to help you hone your machine learning skills. Suitable for both beginners and experts, this user-friendly platform has all you need to build and train machine learning models (including a library of pre-trained models). Tensorflow is more powerful than other libraries and focuses on deep learning, making it perfect for complex projects with large-scale data. Like with most open-source tools, it has a strong community and some tutorials to help you get started.

Now that you know what machine learning is, its types, and its importance, let us move on to the uses of machine learning. In this case, the model tries to figure out whether the data is an apple or another fruit. Once the model has been trained well, it will identify that the data is an apple and give the desired response. High performance graphical processing units (GPUs) are ideal because they can handle a large volume of calculations in multiple cores with copious memory available. However, managing multiple GPUs on-premises can create a large demand on internal resources and be incredibly costly to scale. Use this Machine Learning Engineer job description template to attract software engineers who specialize in machine learning.

The famous “Turing Test” was created in 1950 by Alan Turing, which would ascertain whether computers had real intelligence. It has to make a human believe that it is not a computer but a human instead, to get through the test. Arthur Samuel developed the first computer program that could learn as it played the game of checkers in the year 1952. The first neural network, called the perceptron was designed by Frank Rosenblatt in the year 1957. Machine learning is the core of some companies’ business models, like in the case of Netflix’s suggestions algorithm or Google’s search engine. Other companies are engaging deeply with machine learning, though it’s not their main business proposition.

Unsupervised learning contains data only containing inputs and then adds structure to the data in the form of clustering or grouping. The method learns from previous test data that hasn’t been labeled or categorized and will then group the raw data based on commonalities (or lack thereof). Cluster analysis uses unsupervised learning to sort through giant lakes of raw data to group certain data points together. Clustering is a popular tool for data mining, and it is used in everything from genetic research to creating virtual social media communities with like-minded individuals.

However, some believe that end-to-end deep learning solutions will render expert handcrafted input to become moot. There have already been prior research into the practical application of end-to-end deep learning to avoid the process of manual feature engineering. However, deeper insight into these end-to-end deep learning models — including the percentage of easily detected unknown malware samples — is difficult to obtain due to confidentiality reasons. Another type is instance-based machine learning, which correlates newly encountered data with training data and creates hypotheses based on the correlation.

Predictive analytics using machine learning

We hope that some of these principles will clarify how ML is used, and how to avoid some of the common pitfalls that companies and researchers might be vulnerable to in starting off on an ML-related project. The rapid evolution in Machine Learning (ML) has caused a subsequent rise in the use cases, demands, and the sheer importance of ML in modern life. This is, in part, due to the increased sophistication of Machine Learning, which enables the analysis of large chunks of Big Data. Machine Learning has also changed the way data extraction and interpretation are done by automating generic methods/algorithms, thereby replacing traditional statistical techniques. In order to thrive in this position, you must possess exceptional skills in statistics and programming, as well as a deep understanding of data science and software engineering principles.

Things like growing volumes and varieties of available data, computational processing that is cheaper and more powerful, affordable data storage. Composed of a deep network of millions of data points, DeepFace leverages 3D face modeling to recognize faces in images in a way very similar to that of humans. Machine learning has been a field decades in the making, as scientists and professionals have sought to instill human-based learning methods in technology. The retail industry relies on machine learning for its ability to optimize sales and gather data on individualized shopping preferences. Machine learning offers retailers and online stores the ability to make purchase suggestions based on a user’s clicks, likes and past purchases. Once customers feel like retailers understand their needs, they are less likely to stray away from that company and will purchase more items.

Association rule learning is a method of machine learning focused on identifying relationships between variables in a database. One example of applied association rule learning is the case where marketers use large sets of super market transaction data to determine correlations between different product purchases. For instance, “customers buying pickles and lettuce are also likely to buy sliced cheese.” Correlations or “association rules” like this can be discovered using association rule learning. Semi-supervised learning is actually the same as supervised learning except that of the training data provided, only a limited amount is labelled. It may be through a mathematical process to systematically reduce redundancy, or it may be to organize data by similarity.

Machine learning, however, is most likely to continue to be a major force in many fields of science, technology, and society as well as a major contributor to technological advancement. The creation of intelligent assistants, personalized healthcare, and self-driving automobiles are some potential future uses for machine learning. Important global issues like poverty and climate change may be addressed via machine learning.

Furthermore, attempting to use it as a blanket solution i.e. “BLANK” is not a useful exercise; instead, coming to the table with a problem or objective is often best driven by a more specific question – “BLANK”. At Emerj, the AI Research and Advisory Company, many of our enterprise clients feel as though they should be investing in machine learning projects, but they don’t have a strong grasp of what it is. We often direct them to this resource to get them started with the fundamentals of machine learning in business. These prerequisites will improve your chances of successfully pursuing a machine learning career. For a refresh on the above-mentioned prerequisites, the Simplilearn YouTube channel provides succinct and detailed overviews.

There are many machine learning models, and almost all of them are based on certain machine learning algorithms. Popular classification and regression algorithms fall under supervised machine learning, and clustering algorithms are generally deployed in unsupervised machine learning scenarios. Supervised learning algorithms and supervised learning models make predictions based on labeled training data. A supervised learning algorithm analyzes this sample data and makes an inference – basically, an educated guess when determining the labels for unseen data. Neural networks are a commonly used, specific class of machine learning algorithms.

As technology continues to evolve, machine learning is used daily, making everything go more smoothly and efficiently. If you’re interested in IT, machine learning and AI are important topics that are likely to be part of your future. The more you understand machine learning, the more likely you are to be able to implement it as part of your future career.

Restricted Boltzmann machines (RBM) [46] can be used for dimensionality reduction, classification, regression, collaborative filtering, feature learning, and topic modeling. A deep belief network (DBN) is typically composed of simple, unsupervised networks such as restricted Boltzmann machines (RBMs) or autoencoders, and a backpropagation neural network (BPNN) [123]. A generative adversarial network (GAN) [39] is a form of the network for deep learning that can generate data with characteristics close to the actual data input. Transfer learning is currently very common because it can train deep neural networks with comparatively low data, which is typically the re-use of a new problem with a pre-trained model [124].

Reinforcement machine learning algorithms are a learning method that interacts with its environment by producing actions and discovering errors or rewards. The most relevant characteristics of reinforcement learning are trial and error search and delayed reward. This method allows machines and software agents to automatically determine the ideal behavior within a specific context to maximize its performance. Simple reward feedback — known as the reinforcement signal — is required for the agent to learn which action is best. Today we are witnessing some astounding applications like self-driving cars, natural language processing and facial recognition systems making use of ML techniques for their processing.

Unsupervised learning involves just giving the machine the input, and letting it come up with the output based on the patterns it can find. You can foun additiona information about ai customer service and artificial intelligence and NLP. This kind of machine learning algorithm tends to have more errors, simply because you aren’t telling the program what the answer is. But unsupervised learning helps machines learn and improve based on what they observe. Algorithms in unsupervised learning are less complex, as the human intervention is less important. This dynamic sees itself played out in applications as varying as medical diagnostics or self-driving cars.

Watch a discussion with two AI experts about machine learning strides and limitations. Through intellectual rigor and experiential learning, this full-time, two-year MBA program develops leaders who make a difference in the world. Even after the ML model is in production and continuously monitored, the job continues. Business requirements, technology capabilities and real-world data change in unexpected ways, potentially giving rise to new demands and requirements.

Enterprise machine learning gives businesses important insights into customer loyalty and behavior, as well as the competitive business environment. A classifier is a machine learning algorithm that assigns an object as a member of a category or group. For example, classifiers are used to detect if an email is spam, or if a transaction is fraudulent. To be successful in nearly any industry, organizations must be able to transform their data into actionable insight. Artificial Intelligence and machine learning give organizations the advantage of automating a variety of manual processes involving data and decision making. Below is a breakdown of the differences between artificial intelligence and machine learning as well as how they are being applied in organizations large and small today.

In this case, the model the computer first creates might predict that anything in an image that has four legs and a tail should be labeled dog. With each iteration, the predictive model becomes more complex and more accurate. The fundamental goal of machine learning algorithms is to generalize beyond the training samples i.e. successfully interpret data that it has never ‘seen’ before. For starters, machine learning is a core sub-area of Artificial Intelligence (AI).

By analyzing a known training dataset, the learning algorithm produces an inferred function to predict output values. It can also compare its output with the correct, intended output to find errors and modify the model accordingly. Semisupervised learning works by feeding a small amount of labeled training data to an algorithm. From this data, the algorithm learns the dimensions of the data set, which it can then apply to new unlabeled data. The performance of algorithms typically improves when they train on labeled data sets.

In comparison to sequence mining, association rule learning does not usually take into account the order of things within or across transactions. A common way of measuring the usefulness of association rules is to use its parameter, the ‘support’ and ‘confidence’, which is introduced in [7]. Machine learning (ML) is coming into its own, with a growing recognition that ML can play a key role in a wide range of critical applications, such as data mining, natural language processing, image recognition, and expert systems. ML provides potential solutions in all these domains and more, and likely will become a pillar of our future civilization. Deep learning is a subfield within machine learning, and it’s gaining traction for its ability to extract features from data. Deep learning uses Artificial Neural Networks (ANNs) to extract higher-level features from raw data.

Cancer researchers have also started implementing deep learning into their practice as a way to automatically detect cancer cells. Self-driving cars are also using deep learning to automatically detect objects such as road signs or pedestrians. And social media platforms can use deep learning for content moderation, combing through images and audio. Currently, deep learning is used in common technologies, such as in automatic facial recognition systems, digital assistants and fraud detection. However, they all function in somewhat similar ways — by feeding data in and letting the model figure out for itself whether it has made the right interpretation or decision about a given data element. Google’s DeepMind Technologies developed a system capable of learning how to play Atari video games using only pixels as data input.

Train, validate, tune and deploy generative AI, foundation models and machine learning capabilities with IBM watsonx.ai, a next-generation enterprise studio for AI builders. While this topic garners a lot of public attention, many researchers are not concerned with the idea of AI surpassing human intelligence in the near future. Technological singularity is also referred to as strong AI or superintelligence. It’s unrealistic to think that a driverless car would never have an accident, but who is responsible and liable under those circumstances? Should we still develop autonomous vehicles, or do we limit this technology to semi-autonomous vehicles which help people drive safely?

In this case, the unknown data consists of apples and pears which look similar to each other. The trained model tries to put them all together so that you get the same things in similar groups. As a Machine Learning Engineer, you will play a crucial role in the development and implementation of cutting-edge artificial intelligence products. That is, while we can see that there is a pattern to it (i.e., employee satisfaction tends to go up as salary goes up), it does not all fit neatly on a straight line. This will always be the case with real-world data (and we absolutely want to train our machine using real-world data). How can we train a machine to perfectly predict an employee’s level of satisfaction?

If you’re working with sentiment analysis, you would feed the model with customer feedback, for example, and train the model by tagging each comment as Positive, Neutral, and Negative. One of the most common types of unsupervised learning is clustering, which consists of grouping similar data. This method is mostly used for exploratory analysis and can help you detect hidden patterns or trends. The machine learning process begins with observations or data, such as examples, direct experience or instruction. It looks for patterns in data so it can later make inferences based on the examples provided. The primary aim of ML is to allow computers to learn autonomously without human intervention or assistance and adjust actions accordingly.

But how does a neural network work?

Scikit-learn is a popular Python library and a great option for those who are just starting out with machine learning. You can use this library for tasks such as classification, clustering, and regression, among others. Open source machine learning libraries offer collections of pre-made models and components that developers can use to build their own applications, instead of having to code from scratch. When you’re ready to get started with machine learning tools it comes down to the Build vs. Buy Debate. If you have a data science and computer engineering background or are prepared to hire whole teams of coders and computer scientists, building your own with open-source libraries can produce great results.

The algorithm achieves a close victory against the game’s top player Ke Jie in 2017. This win comes a year after AlphaGo defeated grandmaster Lee Se-Dol, taking four out of the five games. The device contains cameras and sensors that allow it to recognize faces, voices and movements.

In 2013, Trend Micro open sourced TLSH via GitHub to encourage proactive collaboration. To accurately assign reputation ratings to websites (from pornography to shopping and gambling, among others), Trend Micro has been using machine learning technology in its Web Reputation Services since 2009. A Connected Threat Defense for Tighter SecurityLearn how Trend Micro’s Connected Threat Defense can improve an organizations security Chat GPT against new, 0-day threats by connecting defense, protection, response, and visibility across our solutions. Automate the detection of a new threat and the propagation of protections across multiple layers including endpoint, network, servers, and gateway solutions. A popular example are deepfakes, which are fake hyperrealistic audio and video materials that can be abused for digital, physical, and political threats.

One important point (based on interviews and conversations with experts in the field), in terms of application within business and elsewhere, is that machine learning is not just, or even about, automation, an often misunderstood concept. If you think this way, you’re bound to miss the valuable insights that machines can provide and the resulting opportunities (rethinking an entire business model, for example, as has been in industries like manufacturing and agriculture). Machine learning research is part of research on artificial intelligence, seeking to provide knowledge to computers through data, observations and interacting with the world. That acquired knowledge allows computers to correctly generalize to new settings. This program gives you in-depth and practical knowledge on the use of machine learning in real world cases.

Unsupervised machine learning can find patterns or trends that people aren’t explicitly looking for. For example, an unsupervised machine learning program could look through online sales data and identify different types of clients making purchases. Machine learning also performs manual tasks that are beyond our ability to execute at scale — for example, processing the huge quantities of data generated today by digital devices. Machine learning’s ability to extract patterns and insights from vast data sets has become a competitive differentiator in fields ranging from finance and retail to healthcare and scientific discovery. Many of today’s leading companies, including Facebook, Google and Uber, make machine learning a central part of their operations.

Comparing approaches to categorizing vehicles using machine learning (left) and deep learning (right). Use regression techniques if you are working with a data range or if the nature of your response is a real number, such as temperature or the time until failure for a piece of equipment. For example, they can learn to recognize stop signs, identify intersections, and make decisions based on what they see. Natural Language Processing gives machines the ability to break down spoken or written language much like a human would, to process “natural” language, so machine learning can handle text from practically any source.

The financial services industry is championing machine learning for its unique ability to speed up processes with a high rate of accuracy and success. What has taken humans hours, days or even weeks to accomplish can now be executed in minutes. There were over 581 billion transactions processed in 2021 on card brands like American Express.

The advantage of deep learning is the program builds the feature set by itself without supervision. If you’re studying what is Machine Learning, you should familiarize yourself with standard Machine Learning algorithms and processes. These include neural networks, decision trees, random forests, associations, and sequence discovery, gradient boosting and bagging, support vector machines, self-organizing maps, k-means clustering, Bayesian networks, Gaussian mixture models, and more. Another process called backpropagation uses algorithms, like gradient descent, to calculate errors in predictions and then adjusts the weights and biases of the function by moving backwards through the layers in an effort to train the model. Together, forward propagation and backpropagation allow a neural network to make predictions and correct for any errors accordingly.

The machine learning program learned that if the X-ray was taken on an older machine, the patient was more likely to have tuberculosis. It completed the task, but not in the way the programmers intended or would find useful. Some data is held out from the training data to be used as evaluation data, which tests how accurate the machine learning model is when it is shown new data. The result is a model that can be used in the future with different sets of data.

As a result, deep learning may sometimes be referred to as deep neural learning or deep neural network (DDN). Where human brains have millions of interconnected neurons that work together to learn information, deep learning features neural networks constructed from multiple layers of software nodes that work together. Deep learning models are trained using a large set of labeled data and neural network architectures. Deep learning is a subset of machine learning that uses multi-layered neural networks, called deep neural networks, to simulate the complex decision-making power of the human brain. Some form of deep learning powers most of the artificial intelligence (AI) in our lives today. Supervised machine learning algorithms apply what has been learned in the past to new data using labeled examples to predict future events.

Machine learning algorithms create a mathematical model that, without being explicitly programmed, aids in making predictions or decisions with the assistance of sample historical data, or training data. For the purpose of developing predictive models, machine learning brings together statistics and computer science. Algorithms that learn from historical data are either constructed or utilized in machine learning. The performance will rise in proportion to the quantity of information we provide. Supervised learning is a type of machine learning in which the algorithm is trained on the labeled dataset.

Medical professionals, equipped with machine learning computer systems, have the ability to easily view patient medical records without having to dig through files or have chains of communication with other areas of the hospital. Updated medical systems can now pull up pertinent health information on each patient in the blink of an eye. With tools and functions for handling big data, as well as apps to make machine learning accessible, MATLAB is an ideal environment for applying machine learning to your data analytics. Consider using machine learning when you have a complex task or problem involving a large amount of data and lots of variables, but no existing formula or equation.

While this doesn’t mean that ML can solve all arbitrarily complex problems—it can’t—it does make for an incredibly flexible and powerful tool. The field is vast and is expanding rapidly, being continually partitioned and sub-partitioned into different sub-specialties and types of machine learning. With the ever increasing cyber threats that businesses face today, machine learning is needed to secure valuable data and keep hackers out of internal networks.

This subcategory of AI uses algorithms to automatically learn insights and recognize patterns from data, applying that learning to make increasingly better decisions. Many algorithms have been proposed to reduce data dimensions in the machine learning and data science literature [41, 125]. Machine learning is growing in importance due to machine learning description increasingly enormous volumes and variety of data, the access and affordability of computational power, and the availability of high speed Internet. These digital transformation factors make it possible for one to rapidly and automatically develop models that can quickly and accurately analyze extraordinarily large and complex data sets.

• In reinforcement learning, the algorithm is made to train itself using many trial and error experiments.
• Retailers rely on machine learning to capture data, analyze it and use it to personalize a shopping experience, implement a marketing campaign, price optimization, merchandise planning, and for customer insights.
• Supervised learning is the most practical and widely adopted form of machine learning.
• Your understanding of ML could also bolster the long-term results of your artificial intelligence strategy.
• It helps organizations scale production capacity to produce faster results, thereby generating vital business value.

Machine learning techniques include both unsupervised and supervised learning. Launched over a decade ago (and acquired by Google in 2017), Kaggle has a learning-by-doing philosophy, and it’s renowned for its competitions in which participants create models to solve real problems. Check out this online machine learning course in Python, which will have you building your first model in next to no time.

Amid the enthusiasm, companies will face many of the same challenges presented by previous cutting-edge, fast-evolving technologies. New challenges include adapting legacy infrastructure to machine learning systems, mitigating ML bias and figuring out how to best use these awesome new powers of AI to generate profits for enterprises, in spite of the costs. Determine what data is necessary to build the model and whether it’s in shape for model ingestion. Questions should include how much data is needed, how the collected data will be split into test and training sets, and if a pre-trained ML model can be used.

The learning algorithm receives a set of inputs along with the corresponding correct outputs, and the algorithm learns by comparing its actual output with correct outputs to find errors. Through methods like classification, regression, prediction and gradient boosting, supervised learning uses patterns to predict the values of the label on additional unlabeled data. Supervised learning is commonly used in applications where historical data predicts likely future events.

Because the model’s first few iterations involve somewhat educated guesses on the contents of an image or parts of speech, the data used during the training stage must be labeled so the model can see if its guess was accurate. Unstructured data can only be analyzed by a deep learning model once it has been trained and reaches an acceptable level of accuracy, but deep learning models can’t train on unstructured data. Fundamentally, deep learning refers to a class of machine learning algorithms in which a hierarchy of layers is used to transform input data into a slightly more abstract and composite representation. For example, in an image recognition model, the raw input may be an image (represented as a tensor of pixels). Thus, the ultimate success of a machine learning-based solution and corresponding applications mainly depends on both the data and the learning algorithms.