What Is Deep Learning?
DeepLearning is a subset of machine learning which in turn is a subset of artificial intelligence.
 artificial intelligence is a technique that enables a machine to mimic human behavior, machine learning is a technique to achieve artificial intelligence through algorithms trained with data and finally, deep learning is a type of machine learning inspired by the structure of a human brain in terms of deep learning, this structure is called an artificial neural network.

DeepLearning is an AI(Artificial Intelligence) function that imitates the workings of the human brain in processing data and creating patterns for use in decision making. Deep learning is a network that capable of learning unsupervised from data that is unstructured or unlabeled, It is also known as deep neural learning or deep neural network.

Deep learning vs. machine learning

I mentioned in a first-line that deep learning is a form of machine learning. It refers to non-deep machine learning as classical machine learning, to conform to common usage.

in simple we can that, classical machine learning algorithms run much faster than deep learning algorithms; one or more CPUs will often be sufficient to train a classical model. Deep learning models frequently need hardware accelerators such as GPUs, TPUs, or FPGAs for training, and also for deployment at scale. because of them, the models would take months to train.

For lots of problems, some classical machine learning algorithm will produce a “good-enough” model. For another problems, classical machine learning algorithms have not worked terribly well in the past.
In the  most common AI(Artificial Intelligence)techniques used for processing big data is machine learning, a self-adaptive algorithm that gets increasingly better analysis and patterns with experience or with newly added data
on condition that or If a digital payments company wanted to detect the occurrence or potential for fraud in its system, it could employ machine learning tools for this purpose. The algorithm of a computational built into a computer model will process all transactions happening on the digital platform, find patterns in the data set, and point out any anomaly detected by the pattern.
DeepLearning, a subset of machine learning, utilizes a hierarchical level of artificial neural networks to carry out the process of machine learning. The deep learning or artificial neural networks are built like the human brain, with neuron nodes connected together like a web. 

The neurons are grouped into three different types of layers:
  1. Input Layer
  2. Hidden Layer(s)
  3. Output Layer
  • The input layer receives input data. we have four neurons in the input layer:  Departure Date,  Airline, Destination Airport, Origin Airport. The input layer passes inputs to the first hidden layer.
  • The hidden layers perform the mathematical computations on the inputs. One of the best challenges in creating neural networks is deciding the number of hidden layers, as well as the number of neurons for each layer. A deep Learning name has a "Deep" word which refers to having more than one hidden layer.
  • The output layer is the type layer of Deep learning that returns the output data. In our case, the output layer gives us price prediction.

Top Applications of Deep Learning Across Industries
  • Self Driving Cars
  • News Aggregation and Fraud News Detection
  • Natural Language Processing
  • Virtual Assistants
  • Entertainment
  • Visual Recognition
  • Fraud Detection
  • Healthcare

  • Personalizations
  • Detecting Developmental Delay in Children
  • Colorisation of Black and White images
  • Adding sounds to silent movies
  • Automatic Machine Translation
  • Automatic Handwriting Generation
  • Automatic Game Playing
  • Language Translations
  • Pixel Restoration
  • Photo Descriptions
  • Demographic and Election Predictions
  • Deep Dreaming

Advantages of Deep Learning
  • DeepLearning is robust enough to understand and use novel data, but most data scientists have learned to control the learning to focus on what’s important to them. Deep learning takes advantage of this by allowing you to control the learning, but not statistical modeling.
  • DeepLearning allows us to teach a specific task rather than teaching the system of how to learn. always we can use different examples to train a particular model or we can use a very simple training set and simply ask it to learn.
  • it can become any kind of system. It can be for one thing, such as just a face recognition, or for another, such as image reconstruction. It can be with a large number of weights, or with a very small number. It can be linear or nonlinear.
  • it will be much harder to determine where the flaws exist, or where it is creating false positives.
  • it is not affected by computation power. that's why, it can gain insights much more quickly, and thus, it can tackle problems that are traditionally tricky to solve.
  • it has high dimensionality. It means that we can create more learning models by adding more layers to our neural network.
  • it allows us to study the world as a non-supervised structure. If you look at neurons, they have such varied functions and shapes.
  • it can go and get a new image from its own memory.
  • DeepLearning can adapt automatically to all data, but it makes for a nice alternative to traditional machine learning that relies on human expertise
  • DeepLearning handles everything at a much higher level of abstraction than your standard neural network, so the training process is, at its core, much less complex.
  • DeepLearning allows us to retain a lot of information, even on the basis of a very tiny or badly known object. And we are in the process of learning these ways of achieving efficiency for the vision.
  • it can see more than one and can learn with more information.
  • it gets its results more quickly. It learns over time rather than just in a flash.
  • it can learn over time, over billions of examples of images, and, crucially, recognize patterns.
  • DeepLearning can be used in datasets that are too large, complex, and repetitive for traditional computer systems.
  • DeepLearning can handle large amounts of data for small networks with a much lower learning cost.

Disadvantages of Deep Learning
  • DeepLearning is much harder to compare what it achieves to that of hand-crafted methods. It has an alternative approach, called “deep learning by gradient descent”, which can be considered as an extension of deep learning to higher-dimensional regions.
  • DeepLearning is very difficult to assess its performance in real-world applications; applications can vary greatly from application to application, and testing techniques for analysis, validation, and scaling vary widely.
  • DeepLearning is not 100% efficient and it will have some difficult problems.
  • DeepLearning can be trained on very large amounts of data (think thousands of images or videos).
  • DeepLearning doesn’t give us a ton of accurate data. What you’re getting are approximate statistics.
  • DeepLearning tends to learn on its own, and it’s also hard to see the evolution of a system in time.
  • DeepLearning requires huge data sets in order to train. It can be huge, especially when you consider that we only know the image and not the context.
  • DeepLearning doesn’t tend to have as good a learning speed as other methods, or as good a memory as more traditional approaches.
  • DeepLearning is very hard to understand. Thus, It is the next step in machine learning. It allows machines to be more and more sophisticated by learning something more about the world, and then be able to draw a generalization from this knowledge and in the future apply it to another problem.
  • DeepLearning is computationally very expensive, requiring a large amount of memory and computational resources, and it is not easy to transfer it to other problems.
  • DeepLearning requires to train the model to learn about deep structures, a process that requires billions of hours of computation in highly parallel computer architecture.
  • it is hard to describe and is not completely understood.
  • it is a little bit complicated. I do believe the second generation methods are simpler and give a better result.
  • it tends to be more costly.
  • it requires much larger datasets with many more features. As a result, it takes longer to train the algorithm and it takes more memory for it to work with the data.
  • DeepLearning requires very advanced optimization techniques, and these should have been incorporated to obtain good results.


Post a Comment

Previous Post Next Post