One of the most significant advantages of deep learning is its ability to replace the labor-intensive process of manual feature engineering. In traditional machine learning, domain experts crafted specific algorithms to transform raw perceptual data into feature vectors. Deep learning replaces these domain-specific preprocessing steps with automatically tuned filters that are learned jointly from the data, yielding superior accuracy and providing a unified approach across diverse fields.

University of Michigan - Ann Arbor

Claude

Goodfellow, I., Bengio, Y., & Courville, A. (2016). $\mathit{Deep \ Learning.}$ MIT Press. Retrieved from [www.deeplearningbook.org](https://www.deeplearningbook.org) 

Deep Learning

In a machine learning dataset, a feature (also referred to as an input or covariate) is an individual, measurable attribute of a given data point. A model relies on these numerical representations to make its predictions.

Machine Learning Feature

https://magnimindacademy.com/blog/deep-learning-and-its-5-advantages#:~:text=One%20of%20the%20biggest%20advantages,told%20to%20do%20so%20explicitly.

DEEP LEARNING AND ITS 5 ADVANTAGES

Dive into Deep Learning

The universal approximation theorem (Horniket al., 1989; Cybenko, 1989) states that a feedforward network with a linear output layer and at least one hidden layer with any “squashing” activation function (such as the logistic sigmoid activation function) can approximate any Borel measurable function from one ﬁnite-dimensional space to another with any desired nonzero amount of error, provided that the network is given enough hidden units. The derivatives of the feedforward network can also approximate the derivatives of the function arbitrarily well.

It means that regardless of what function we are trying to learn, we know that a large feedforward network will be able to represent this function. 

Universal Approximation Theorem

The illustration below shows the relationship between the fields of Artificial Intelligence. Deep learning is a subset of machine learning. 

Refernce : https://lupinepublishers.com/material-science-journal/pdf/MAMS.MS.ID.000138.pdf

Set relationship of Artificial Intelligence

The possibility of Deep Learning is enormous, but it also has a limitation which we need to understand for better utilization. 

a. The systems need 10,000+ examples to learn a concept
like cows. Humans only need a handful of examples.

b. Deep Learning cannot explain how the systems got an
answer.

c. Deep Learning lacks common sense. This makes the
systems fragile and when errors are made, the errors can be
very large.


Limitation of Deep Learning

- It requires very large amount of data in order to perform better than other techniques.

- It is extremely expensive to train due to complex data models. Moreover deep learning requires expensive GPUs and hundreds of machines. This increases cost to the users.

- There is no standard theory to guide you in selecting right deep learning tools as it requires knowledge of topology, training method and other parameters. As a result it is difficult to be adopted by less skilled people.

- It is not easy to comprehend output based on mere learning and requires classifiers to do so. Convolutional neural network based algorithms perform such tasks.

Drawbacks or disadvantages of Deep Learning

In this node, we describe how to use deep learning to solve applications in computer vision, speech recognition, natural language processing, and other areas of commercial interest. 

Applications of Deep Learning

Automated Feature Engineering

In supervised learning problems, a label, also known as a target, is a special attribute of an example that a model aims to predict. It represents the known outcome or ground truth that is not part of the model's input features.

Machine Learning Label

In machine learning, image data is often represented numerically. For instance, a color photograph can be represented as three grids of numerical values corresponding to the brightness of red, green, and blue light at each pixel location. Consequently, a $$200 \times 200$$ pixel color image consists of $$200 \times 200 \times 3 = 120000$$ numerical features.

Image Data Representation Example

Electronic health records provide a classic example of tabular data used in machine learning. For example, when predicting whether a patient will survive the next 30 days, the features might include a set of readily available attributes such as age, vital signs, comorbidities, current medications, and recent procedures. The label used for training the model would be a binary value indicating if the patient survived within that 30-day period.

Electronic Health Record Data Example

When machine learning inputs are structured as fixed-length vectors, the constant length of these vectors—meaning the exact number of numerical features—is defined as the dimensionality of the data. For instance, a $$200 	imes 200$$ pixel color image represented by red, green, and blue values has a dimensionality of $$200 	imes 200 	imes 3 = 120000$$.

Learn Before

Related