{"id":5495,"date":"2024-07-25T06:47:53","date_gmt":"2024-07-25T06:47:53","guid":{"rendered":"https:\/\/www.moxoff.com\/?p=5495"},"modified":"2025-09-02T15:00:11","modified_gmt":"2025-09-02T15:00:11","slug":"deep-learning-cose-come-funziona-casi-uso","status":"publish","type":"post","link":"https:\/\/www.moxoff.com\/en\/deep-learning-cose-come-funziona-casi-uso\/","title":{"rendered":"Deep Learning: what it is, how it works, and use cases"},"content":{"rendered":"

Born as a specific subset of machine learning (ML)<\/strong>, today deep learning (DL)<\/strong> tands out as one of the most fascinating techniques in the field of artificial intelligence, due to its proclaimed functional resemblance to the human brain. This resemblance also inspires its generalist approach to the problems it seeks to solve.<\/p>\n

Thanks to the proven expertise of Moxoff, which has been engaged for years in developing DL systems within the enterprise sector, we will explore what deep learning consists of, the technologies that characterise it, the main differences compared to machine learning, and the areas of business where it is currently being successfully implemented.<\/p>\n

What is deep learning<\/strong><\/span><\/h2>\n

According to the definition provided by Gartner, deep learning is a \u201cVariant of machine learning algorithms. It uses many layers to solve problems, gaining knowledge from raw data by transforming it at each layer. These layers progressively extract increasingly accurate features from the raw data, enabling the solution of complex problems with a high level of precision and limited human intervention.\u201d<\/p>\n

According to Techtarget: \u201cDeep learning is a type of machine learning that mimics the way humans acquire certain kinds of knowledge. Deep learning models can be trained to perform classification tasks and to recognise patterns in images, text, audio, and various other data. It is also used to automate tasks that would normally require human intelligence, such as describing images or transcribing audio files.\u201d
\nThanks to this inherent capability, deep learning assists data scientists when they need to collect, analyse, and interpret large quantities and varieties of data<\/strong>, due to its strong analogy with the morphology of the human brain. In fact, DL features neural networks made up of multiple layers of nodes that work together in ways comparable to the millions of interconnected neurons in the human brain.<\/p>\n

Deep Learning e Machine Learning<\/span><\/h2>\n

Deep learning is a sub-branch of machine learning, so it is reasonable to expect that DL and ML are based on similar principles, despite the wide variety of technologies that characterise them. However, their use can differ significantly.<\/p>\n

Machine learning operates in more specific fields, offering solutions to problems that are generally known in advance and described through the data sets used to train the algorithms. Deep learning, on the other hand, uses more complex and layered technologies, as well as referring to much broader bodies of knowledge. The \u201cdeep\u201d approach consists of trying to generalise problems without necessarily contextualising them in advance, with the aim of finding solutions according to the logic that the human brain would use when faced with unfamiliar situations.
\nWith the sole intention of providing information, we could summarise the comparison between machine learning and deep learning as follows.<\/p>\n

Machine Learning (compared to DL)<\/em><\/p>\n

    \n
  1. It uses algorithms to learn an approximate representation of the phenomenon to be modelled.<\/li>\n
  2. It is effective even with a smaller dataset.<\/li>\n
  3. Shorter training times.<\/li>\n
  4. Greater simplicity in interpreting the analytical result.<\/li>\n
  5. It requires more limited hardware resources.<\/li>\n<\/ol>\n

    Deep Learning (compared to ML)<\/em><\/p>\n

      \n
    1. It uses algorithms to learn an approximate representation of the phenomenon to be modelled.<\/li>\n
    2. It requires large volumes of data.<\/li>\n
    3. Training times can be very lengthy.<\/li>\n
    4. Effective for complex tasks.<\/li>\n
    5. Results are not always easy to interpret, with a high \"black box\" effect.<\/li>\n
    6. It requires significant computational resources.<\/li>\n<\/ol>\n

      Deep Learning: when and how it originated<\/span><\/h2>\n

      The history of deep learning forms part of the fascinating chronology ofArtificial Intelligence<\/strong>, beginning in 1943, when Warren McCulloch and Walter Pitts created the first computational model for neural networks: \u201cthreshold logic\u201d. In other words, the very first deep learning algorithm.
      \nThe first major milestone in DL was set in 1958, when Frank Rosenblatt introduced the famous perceptron, a pattern recognition algorithm based on a two-layer neural network, using the mathematical principles of addition and subtraction. This marked the beginning of a long period of research and development, which would only bear fruit in 1975.<\/p>\n

      In the following years, other increasingly sophisticated multilayer neural networks made their debut, such as the Neocognitron (1980), designed by Kunihiko Fukushima to tackle tasks like handwritten character recognition and other pattern recognition problems.
      \nDespite the success of research in the field, which led to a flourishing scientific literature on the subject, deep learning\u2014like artificial intelligence more broadly\u2014entered a so-called \"AI winter\" that lasted around twenty years. The main reason for this abrupt slowdown was the complexity of the computations<\/strong> required by deep neural networks, which at the time took many days to run even on supercomputers. These circumstances, although they clearly indicated the potential of the technology, discouraged its adoption in current applications, both in the consumer and enterprise sectors.<\/p>\n

      In the 2010s, thanks to huge advances in computing technologies and the advent of cloud computing, deep learning resumed its rise to prominence\u2014including in the media. This resurgence was demonstrated on various occasions by DeepMind, an AI lab acquired by Google in 2014, which developed applications such as AlphaFold. AlphaFold was able to solve the protein folding problem, quite literally ushering in a new era in the field of molecular biology.
      \nDeep learning applications, fuelled by major incentives from big tech companies, have become part of everyday technology, accessible to everyone, often without users even realising it. One example is DeepFace, a deep learning technology implemented by Facebook for facial recognition and automatic tagging of user profiles. To give an idea of the technological complexity of DL, it is enough to note that the first version of DeepFace used deep neural networks with over 120 million parameters.
      \nToday, deep learning is used in a wide range of business sectors. Thanks to functions such as object detection\/recognition, image classification, and natural language processing, it underpins applications including automatic text and image generation, multilingual simultaneous translation, sentiment analysis and speech recognition.<\/p>\n

      How Deep Learning Works<\/span><\/h2>\n

      To understand the basic principles of how deep learning works, it is useful to highlight the crucial stages in the development process.<\/p>\n

      Neural network structure<\/h3>\n

      The first step consists of choosing the type of neural network to use. Deep neural networks (with three or more layers) make use of intermediate layers (hidden layers<\/strong>) to build various levels of abstraction, aiming to use the minimum resources necessary to solve a mathematical problem.
      \nThe expertise of the data scientist and data engineer in optimising resources according to the required level of complexity is fundamental in this context. A deep neural network with many hidden layers can achieve highly accurate results, but this comes at the cost of increased complexity in terms of dataset definition, mathematical modelling, and the computational resources needed to carry out the necessary processing.<\/p>\n

      Network training<\/h3>\n

      Deep learning systems are trained using labelled data with specific meta tags. A common example is image recognition. A dataset containing images of cows will have a series of files tagged with the metatag \u201ccow\u201d, but no further instructions are given to the system.<\/p>\n

      It is the neural network itself, through the interaction of its various hierarchical layers, that learns to identify the distinctive features of a cow and to recognise it as such. DL systems therefore use a trial and error<\/strong> learning procedure<\/strong>, which requires large datasets in order to generalise the problem.
      \nToday, there are various frameworks available for training deep neural networks. Notable examples include TensorFlow, an open-source library developed by Google, and PyTorch, an open-source project supported by Meta, built on the foundations of the Caffe2 and ONNX frameworks.<\/p>\n

      Backpropagation and optimisation<\/h3>\n

      The morphological complexity of a neural network is reflected in the objective difficulty of adjusting and weighting its various nodes. For training deep neural networks, error backpropagation algorithms are commonly used; these algorithms automatically adjust the weights of neural connections when the outcome does not meet expectations (in the case of an error).
      \nIn other words, the backpropagation algorithm iteratively optimises the result, constantly seeking the most appropriate weights to use based on the estimated error.<\/p>\n

      Testing and validation<\/h3>\n

      In machine learning, datasets are usually divided into three types: training<\/strong>, validation<\/strong> and test set<\/strong>This approach allows the model to be trained on one set, tested and refined with a second set, and validated with a further set. Such a procedure offers obvious advantages when working with large datasets, as is common in deep learning.<\/p>\n

      This is a process that requires skills and experience that cannot be improvised. Determining the appropriate sizes for the training, validation, and test sets depends on various factors, such as the size of the dataset, its complexity, the number of model parameters, and the nature of the problem being addressed.
      \nYears of proven field experience now enable Moxoff to make the most effective decisions regarding the definition of datasets used for training deep learning systems.<\/p>\n

      Implementation<\/h3>\n

      Once developed, a deep learning application can be implemented to deliver rapid results, even for highly complex tasks. However, as expressly recommended by the recent (AI Act)<\/strong>it is always advisable to establish an appropriate workflow for monitoring and evaluating results, aimed at assessing the validity of outcomes over time, ensuring compliance with regulatory requirements, and updating documentation to explain the functioning of the AI system itself.<\/p>\n

      Key components of deep learning<\/span><\/h2>\n

      The terminology of deep learning refers to at least the following key components: artificial neurons, neural networks, and activation functions.<\/p>\n

      Artificial neurons<\/h3>\n

      Artificial neurons are the fundamental components of mathematical models known as neural networks, whose operational scheme is explicitly inspired by the neural connections in the biological brain. Neurons are linked in successive layers by weighted connections, numerical values multiplied by each neuron's value. Artificial neurons are present at all levels of the neural network: input, hidden (intermediate), and output, and they effectively govern how the network operates.<\/p>\n

      Neural networks<\/h3>\n

      A neural network is traditionally composed of three types of layers: input, hidden (intermediate), and output layers.<\/p>\n