Deep learning

Deep learning 

Deep learning is a set of machine learning algorithms that model high-level abstractions in data using architectures consisting of multiple nonlinear transformations. A deep learning technology is based on ANNs. These ANNs constantly receive learning algorithms and continuously growing amounts of data to increase the efficiency of training processes.

Advantage and disadvantages of Deep learning is a machine learning framework.

Advantages

·         Has best-in-class performance on problems that significantly outperforms other solutions in multiple domains. This includes speech, language, vision, playing games like Go etc. This isn’t by a little bit, but by a significant amount.

·         Reduces the need for feature engineering, one of the most time-consuming parts of machine learning practice.

·         Is an architecture that can be adapted to new problems relatively easily (e.g. Vision, time series, language etc using techniques like convolutional neural networks, recurrent neural networks, long short-term memory etc.

Disadvantages

·         Requires a large amount of data — if you only have thousands of example, deep learning is unlikely to outperform other approaches.

·         Is extremely computationally expensive to train. The most complex models take weeks to train using hundreds of machines equipped with expensive GPUs.

·         Do not have much in the way of a strong theoretical foundation. This leads to the next disadvantage.

·         Determining the topology/flavor/training method/hyperparameters for deep learning is a black art with no theory to guide you.

·         What is learned is not easy to comprehend. Other classifiers (e.g. decision trees, logistic regression etc) make it much easier to understand what’s going on.

Applications

Automatic speech recognition

large-scale automatic speech recognition is the first and most convincing successful case of deep learning. LSTM RNNs can learn "Very Deep Learning" tasks^[2] that involve multi-second intervals containing speech events separated by thousands of discrete time steps, where one-time step corresponds to about 10 ms. LSTM with forget gates^[107] is competitive with traditional speech recognizers on certain tasks.

The initial success in speech recognition was based on small-scale recognition tasks based on TIMIT. The dataset contains 630 speakers from eight major dialects of American English, where each speaker reads 10 sentences. Its small size lets many configurations be tried. More importantly, the TIMIT task concerns phone-sequence recognition, which, unlike word-sequence recognition, allows weak phone bigram language models.

Image recognition

A common evaluation set for image classification is the MNIST database data set. MNIST is composed of handwritten digits and includes 60,000 training examples and 10,000 test examples. As with TIMIT, its small size lets users test multiple configurations. A comprehensive list of results on this set is available.

Deep learning-based image recognition has become "superhuman", producing more accurate results than human contestants. This first occurred in 2011

Visual art processing

Closely related to the progress that has been made in image recognition is the increasing application of deep learning techniques to various visual art tasks. DNNs have proven themselves capable, for example, of a) identifying the style period of a given painting, b) "capturing" the style of a given painting and applying it in a visually pleasing manner to an arbitrary photograph, and c) generating striking imagery based on random visual input fields

Natural language processing

Neural networks have been used for implementing language models since the early 2000s. LSTM helped to improve machine translation and language modeling.

Other key techniques in this field are negative sampling and word embedding. Word embedding, such as word2vec, can be thought of as a representational layer in a deep learning architecture that transforms an atomic word into a positional representation of the word relative to other words in the dataset; the position is represented as a point in a vector space. Using word embedding as an RNN input layer allows the network to parse sentences and phrases using an effective compositional vector grammar. A compositional vector grammar can be thought of as probabilistic context-free grammar (PCFG) implemented by an RNN. Recursive auto-encoders built atop word embedding can assess sentence similarity and detect paraphrasing. Deep neural architectures provide the best results for constituency parsing. sentiment analysis, information retrieval, spoken language understanding, machine translation, contextual entity linking,^] writing style recognition, Text classification, and others

Atom Net is a deep learning system for structure-based rational drug design. Atom Net was used to predict novel candidate biomolecules for disease targets such as the Ebola virus^[ and multiple sclerosis.

Customer relationship management

Deep reinforcement learning has been used to approximate the value of possible direct marketing actions, defined in terms of RFM variables. The estimated value function was shown to have a natural interpretation as customer lifetime value.

Recommendation systems

Recommendation systems have used deep learning to extract meaningful features for a latent factor model for content-based music recommendations. Multi-view deep learning has been applied for learning user preferences from multiple domains. The model uses a hybrid collaborative and content-based approach and enhances recommendations in multiple tasks.

Bioinformatics

An autoencoder ANN was used in bioinformatics, to predict gene ontology annotations and gene-function relationships.

In medical informatics, deep learning was used to predict sleep quality based on data from wearables and predictions of health complications from electronic health record data. Deep learning has also shown efficacy in healthcare.

Mobile advertising

Finding the appropriate mobile audience for mobile advertising is always challenging since many data points must be considered and assimilated before a target segment can be created and used in ad serving by any ad server. Deep learning has been used to interpret large, many-dimensioned advertising datasets. Many data points are collected during the request/serve/click internet advertising cycle. This information can form the basis of machine learning to improve ad selection.

Image restoration

Deep learning has been successfully applied to inverse problems such as denoising, super-resolution, and inpainting. These applications include learning methods such as "Shrinkage Fields for Effective Image Restoration which trains on an image dataset, and Deep Image Prior, which trains on the image that needs restoration.

Financial fraud detection

Deep learning is being successfully applied to financial fraud detection and anti-money laundering. "Deep anti-money laundering detection system can spot and recognize relationships and similarities between data and, further down the road, learn to detect anomalies or classify and predict specific events". The solution leverages both supervised learning techniques, such as the classification of suspicious transactions, and unsupervised learning, e.g. anomaly detection. 

What Is the Difference between Deep Learning and Machine Learning?

Deep learning is a kind of traditional machine learning. Classical machine learning is the extraction of new knowledge from a large data array loaded into the machine. Users formulate the machine training rules and correct errors made by a machine. This approach eliminates a negative overtraining effect frequently appearing in deep learning.

In machine learning, users provide a machine with both examples and training data to help the system make correct decisions. This principle is called supervised learning. In other words, in a classical machine learning, a computer solves a large number of tasks, but it cannot form such tasks without a human control.

Diversity between machine learning (ML) and deep learning (DL):

·   DL requires a lot of unlabeled training data to make concise conclusions while ML can use small data amounts provided by users.

·   Unlike ML, DL needs high-performance hardware.

·    ML requires features to be accurately identified by users while DL creates new features by itself.

·    ML divides tasks into small pieces and then combine received results into one conclusion while DL solves the problem on the end-to-end basis.

·    In comparison with ML, DL needs much more time to train.

·    Unlike DL, ML can provide enough transparency for its decisions.

The concept of deep learning implies that the machine creates its functionality by itself as long as it is possible at the current time. To infer, deep learning applications use a hierarchical approach involving determining the most important characteristics to compare.