AI News, Machine Learning Department - School of Computer Science

Machine Learning Department - School of Computer Science

Building intelligent machines that are capable of extracting meaningful representations from high-dimensional data lies at the core of solving many AI related tasks.

An important property of these models is that they can learn useful representations by re-using and combining intermediate concepts, allowing these models to be successfully applied in a wide variety of domains, including visual object recognition, information retrieval, natural language processing, and speech perception.

Deep learning

Learning can be supervised, semi-supervised or unsupervised.[1][2][3] Deep learning architectures such as deep neural networks, deep belief networks and recurrent neural networks have been applied to fields including computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics and drug design,[4] where they have produced results comparable to and in some cases superior[5] to human experts.[6] Deep learning models are vaguely inspired by information processing and communication patterns in biological nervous systems yet have various differences from the structural and functional properties of biological brains, which make them incompatible with neuroscience evidences.[7][8][9] Deep learning is a class of machine learning algorithms that:[10](pp199–200) Most modern deep learning models are based on an artificial neural network, although they can also include propositional formulas[11] or latent variables organized layer-wise in deep generative models such as the nodes in Deep Belief Networks and Deep Boltzmann Machines.

Examples of deep structures that can be trained in an unsupervised manner are neural history compressors[13] and deep belief networks.[1][14] Deep neural networks are generally interpreted in terms of the universal approximation theorem[15][16][17][18][19] or probabilistic inference.[10][11][1][2][14][20][21] The universal approximation theorem concerns the capacity of feedforward neural networks with a single hidden layer of finite size to approximate continuous functions.[15][16][17][18][19] In 1989, the first proof was published by George Cybenko for sigmoid activation functions[16] and was generalised to feed-forward multi-layer architectures in 1991 by Kurt Hornik.[17] The probabilistic interpretation[20] derives from the field of machine learning.

More specifically, the probabilistic interpretation considers the activation nonlinearity as a cumulative distribution function.[20] The probabilistic interpretation led to the introduction of dropout as regularizer in neural networks.[22] The probabilistic interpretation was introduced by researchers including Hopfield, Widrow and Narendra and popularized in surveys such as the one by Bishop.[23] The term Deep Learning was introduced to the machine learning community by Rina Dechter in 1986,[24][13] and to Artificial Neural Networks by Igor Aizenberg and colleagues in 2000, in the context of Boolean threshold neurons.[25][26] The first general, working learning algorithm for supervised, deep, feedforward, multilayer perceptrons was published by Alexey Ivakhnenko and Lapa in 1965.[27] A 1971 paper described a deep network with 8 layers trained by the group method of data handling algorithm.[28] Other deep learning working architectures, specifically those built for computer vision, began with the Neocognitron introduced by Kunihiko Fukushima in 1980.[29] In 1989, Yann LeCun et al.

Each layer in the feature extraction module extracted features with growing complexity regarding the previous layer.[38] In 1995, Brendan Frey demonstrated that it was possible to train (over two days) a network containing six fully connected layers and several hundred hidden units using the wake-sleep algorithm, co-developed with Peter Dayan and Hinton.[39] Many factors contribute to the slow speed, including the vanishing gradient problem analyzed in 1991 by Sepp Hochreiter.[40][41] Simpler models that use task-specific handcrafted features such as Gabor filters and support vector machines (SVMs) were a popular choice in the 1990s and 2000s, because of ANNs' computational cost and a lack of understanding of how the brain wires its biological networks.

In 2003, LSTM started to become competitive with traditional speech recognizers on certain tasks.[51] Later it was combined with connectionist temporal classification (CTC)[52] in stacks of LSTM RNNs.[53] In 2015, Google's speech recognition reportedly experienced a dramatic performance jump of 49% through CTC-trained LSTM, which they made available through Google Voice Search.[54] In 2006, publications by Geoff Hinton, Ruslan Salakhutdinov, Osindero and Teh[55] [56][57] showed how a many-layered feedforward neural network could be effectively pre-trained one layer at a time, treating each layer in turn as an unsupervised restricted Boltzmann machine, then fine-tuning it using supervised backpropagation.[58] The papers referred to learning for deep belief nets.

It was believed that pre-training DNNs using generative models of deep belief nets (DBN) would overcome the main difficulties of neural nets.[69] However, it was discovered that replacing pre-training with large amounts of training data for straightforward backpropagation when using DNNs with large, context-dependent output layers produced error rates dramatically lower than then-state-of-the-art Gaussian mixture model (GMM)/Hidden Markov Model (HMM) and also than more-advanced generative model-based systems.[59][70] The nature of the recognition errors produced by the two types of systems was characteristically different,[71][68] offering technical insights into how to integrate deep learning into the existing highly efficient, run-time speech decoding system deployed by all major speech recognition systems.[10][72][73] Analysis around 2009-2010, contrasted the GMM (and other generative speech models) vs.

While there, Ng determined that GPUs could increase the speed of deep-learning systems by about 100 times.[79] In particular, GPUs are well-suited for the matrix/vector math involved in machine learning.[80][81] GPUs speed up training algorithms by orders of magnitude, reducing running times from weeks to days.[82][83] Specialized hardware and algorithm optimizations can be used for efficient processing.[84] In 2012, a team led by Dahl won the 'Merck Molecular Activity Challenge' using multi-task deep neural networks to predict the biomolecular target of one drug.[85][86] In 2014, Hochreiter's group used deep learning to detect off-target and toxic effects of environmental chemicals in nutrients, household products and drugs and won the 'Tox21 Data Challenge' of NIH, FDA and NCATS.[87][88][89] Significant additional impacts in image or object recognition were felt from 2011 to 2012.

The error rates listed below, including these early results and measured as percent phone error rates (PER), have been summarized over the past 20 years:[clarification needed] The debut of DNNs for speaker recognition in the late 1990s and speech recognition around 2009-2011 and of LSTM around 2003-2007, accelerated progress in eight major areas:[10][74][72] All major commercial speech recognition systems (e.g., Microsoft Cortana, Xbox, Skype Translator, Amazon Alexa, Google Now, Apple Siri, Baidu and iFlyTek voice search, and a range of Nuance speech products, etc.) are based on deep learning.[10][121][122][123] A

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.[127][128] Neural networks have been used for implementing language models since the early 2000s.[102][129] LSTM helped to improve machine translation and language modeling.[103][104][105] Other key techniques in this field are negative sampling[130] and word embedding.

A compositional vector grammar can be thought of as probabilistic context free grammar (PCFG) implemented by an RNN.[131] Recursive auto-encoders built atop word embeddings can assess sentence similarity and detect paraphrasing.[131] Deep neural architectures provide the best results for constituency parsing,[132] sentiment analysis,[133] information retrieval,[134][135] spoken language understanding,[136] machine translation,[103][137] contextual entity linking,[137] writing style recognition,[138] Text classifcation[98] and others.[139] Google Translate (GT) uses a large end-to-end long short-term memory network.[140][141][142][143][144][145] GNMT uses an example-based machine translation method in which the system 'learns from millions of examples.'[141] It translates 'whole sentences at a time, rather than pieces.

These failures are caused by insufficient efficacy (on-target effect), undesired interactions (off-target effects), or unanticipated toxic effects.[149][150] Research has explored use of deep learning to predict biomolecular target,[85][86] off-target and toxic effects of environmental chemicals in nutrients, household products and drugs.[87][88][89] AtomNet is a deep learning system for structure-based rational drug design.[151] AtomNet was used to predict novel candidate biomolecules for disease targets such as the Ebola virus[152] and multiple sclerosis.[153][154] Deep reinforcement learning has been used to approximate the value of possible direct marketing actions, defined in terms of RFM variables.

An autoencoder ANN was used in bioinformatics, to predict gene ontology annotations and gene-function relationships.[158] In medical informatics, deep learning was used to predict sleep quality based on data from wearables[159][160] and predictions of health complications from electronic health record data.[161] Deep learning has also showed efficacy in healthcare.[162][163] 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.[164][165] Deep learning has been used to interpret large, many-dimensioned advertising datasets.

On the one hand, several variants of the backpropagation algorithm have been proposed in order to increase its processing realism.[172][173] Other researchers have argued that unsupervised forms of deep learning, such as those based on hierarchical generative models and deep belief networks, may be closer to biological reality.[174][175] In this respect, generative neural network models have been related to neurobiological evidence about sampling-based processing in the cerebral cortex.[176] Although a systematic comparison between the human brain organization and the neuronal encoding in deep networks has not yet been established, several analogies have been reported.

systems, like Watson (...) use techniques like deep learning as just one element in a very complicated ensemble of techniques, ranging from the statistical technique of Bayesian inference to deductive reasoning.'[189] As an alternative to this emphasis on the limits of deep learning, one author speculated that it might be possible to train a machine vision stack to perform the sophisticated task of discriminating between 'old master' and amateur figure drawings, and hypothesized that such a sensitivity might represent the rudiments of a non-trivial machine empathy.[190] This same author proposed that this would be in line with anthropology, which identifies a concern with aesthetics as a key element of behavioral modernity.[191] In further reference to the idea that artistic sensitivity might inhere within relatively low levels of the cognitive hierarchy, a published series of graphic representations of the internal states of deep (20-30 layers) neural networks attempting to discern within essentially random data the images on which they were trained[192] demonstrate a visual appeal: the original research notice received well over 1,000 comments, and was the subject of what was for a time the most frequently accessed article on The Guardian's[193] web site.

Some deep learning architectures display problematic behaviors,[194] such as confidently classifying unrecognizable images as belonging to a familiar category of ordinary images[195] and misclassifying minuscule perturbations of correctly classified images.[196] Goertzel hypothesized that these behaviors are due to limitations in their internal representations and that these limitations would inhibit integration into heterogeneous multi-component AGI architectures.[194] These issues may possibly be addressed by deep learning architectures that internally form states homologous to image-grammar[197] decompositions of observed entities and events.[194] Learning a grammar (visual or linguistic) from training data would be equivalent to restricting the system to commonsense reasoning that operates on concepts in terms of grammatical production rules and is a basic goal of both human language acquisition[198] and AI.[199] As deep learning moves from the lab into the world, research and experience shows that artificial neural networks are vulnerable to hacks and deception.

Autoencoder

An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner.[1][2] The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for the purpose of dimensionality reduction.

Recently, the autoencoder concept has become more widely used for learning generative models of data.[3][4] Some of the most powerful AI in the 2010s has involved sparse autoencoders stacked inside of deep neural networks.[5]

An autoencoder learns to compress data from the input layer into a short code, and then uncompress that code into something that closely matches the original data.

The first autoencoder might learn to encode easy features like corners, the second to analyze the first layer's output and then encode less local features like the tip of a nose, the third might encode a whole nose, etc., until the final autoencoder encodes the whole image into a code that matches (for example) the concept of 'cat'.[5] An alternative use is as a generative model: for example, if a system is manually fed the codes it has learned for 'cat' and 'flying', it may attempt to generate an image of a flying cat, even if it has never seen a flying cat before.[3][6] Architecturally, the simplest form of an autoencoder is a feedforward, non-recurrent neural network very similar to the many single layer perceptrons which makes a multilayer perceptron (MLP) – having an input layer, an output layer and one or more hidden layers connecting them – but with the output layer having the same number of nodes as the input layer, and with the purpose of reconstructing its own inputs (instead of predicting the target value

R

d

X

R

p

F

x

′

σ

′

W

′

b

′

{\displaystyle \mathbf {\sigma '} ,\mathbf {W'} ,{\text{ and }}\mathbf {b'} }

{\displaystyle \mathbf {\sigma } ,\mathbf {W} ,{\text{ and }}\mathbf {b} }

F

If the hidden layers are larger than the input layer, an autoencoder can potentially learn the identity function and become useless.

However, experimental results have shown that autoencoders might still learn useful features in these cases.[7]:19 Various techniques exist to prevent autoencoders from learning the identity function and to improve their ability to capture important information and learn richer representations: Denoising autoencoders take a partially corrupted input whilst training to recover the original undistorted input.

This technique has been introduced with a specific approach to good representation.[8] A good representation is one that can be obtained robustly from a corrupted input and that will be useful for recovering the corresponding clean input.

This definition contains the following implicit assumptions: To train an autoencoder to denoise data, it is necessary to perform preliminary stochastic mapping

x

~

x

~

x

~

′

x

~

x

~

′

In a sparse autoencoder, there are actually more (rather than fewer) hidden units than inputs, but only a small number of the hidden units are allowed to be active at the same time.[5] Sparsity may be achieved by additional terms in the loss function during training (by comparing the probability distribution of the hidden unit activations with some low desired value),[9] or by manually zeroing all but the few strongest hidden unit activations (referred to as a k-sparse autoencoder).[10] Variational autoencoder models inherit autoencoder architecture, but make strong assumptions concerning the distribution of latent variables.

They use variational approach for latent representation learning, which results in an additional loss component and specific training algorithm called Stochastic Gradient Variational Bayes (SGVB).[3] It assumes that the data is generated by a directed graphical model

K

L

however, alternative configurations have also been recently considered, e.g.[11] Contractive autoencoder adds an explicit regularizer in their objective function that forces the model to learn a function that is robust to slight variations of input values.

The final objective function has the following form: If linear activations are used, or only a single sigmoid hidden layer, then the optimal solution to an autoencoder is strongly related to principal component analysis (PCA).[12][13] The weights of the autoencoder span the same vector subspace as the one spanned by the first

The autoencoder weights are not equal to the principal components, and are generally not orthogonal, yet the principal components may be recovered from them using singular value decomposition.[14] The training algorithm for an autoencoder can be summarized as An autoencoder is often trained using one of the many variants of backpropagation (such as conjugate gradient method, steepest descent, etc.).

This means that the network will almost always learn to reconstruct the average of all the training data.[citation needed] Though more advanced backpropagation methods (such as the conjugate gradient method) can solve this problem to a certain extent, they still result in a very slow learning process and poor solutions.

Stephen Luttrell, while based at RSRE, developed a technique for unsupervised training of hierarchical self-organizing neural nets with 'many hidden layers',[15] which are equivalent to deep autoencoders.

This method involves treating each neighbouring set of two layers as a restricted Boltzmann machine so that the pretraining approximates a good solution, then using a backpropagation technique to fine-tune the results.[16] This model takes the name of deep belief network.

Deep Learning with Tensorflow - Introduction to Unsupervised Learning

Enroll in the course for free at: Deep Learning with TensorFlow Introduction The majority of data ..

Unsupervised Machine Learning

Dr. Ali Shojaie from the University of Washington presents a lecture titled "Unsupervised Machine Learning." View Slides ...

The Next Generation of Neural Networks

Google Tech Talks November, 29 2007 In the 1980's, new learning algorithms for neural networks promised to solve difficult classification tasks, like speech or ...

Deep Neural Network

Jürgen Schmidhuber at AGI-2011: Fast Deep/Recurrent Nets for AGI Vision

The Fourth Conference on Artificial General Intelligence Mountain View, California, USA August 3-6, 2011 Jürgen Schmidhuber's short talk on fast deep neural ...

Deep Learning of Representations

Google Tech Talk 11/13/2012 Presented by Yoshua Bengio ABSTRACT Yoshua Bengio will give an introduction to the area of Deep Learning, to which he has ...

Recent Developments in Deep Learning

Google Tech Talk March 19, 2010 ABSTRACT Presented by Geoff Hinton, University of Toronto. Deep networks can be learned efficiently from unlabeled data.