History Of Artificial Neural Networks

Artificial neural networks (ANNs) are models created using machine learning to perform a number of tasks. Their creation was inspired by neural circuitry. While some of the computational implementations ANNs relate to earlier discoveries in mathematics, the first implementation of ANNs was by psychologist Frank Rosenblatt, who developed the perceptron. Little research was conducted on ANNs in the 1970s and 1980s, with the AAAI calling that period an " AI winter".

Later, advances in hardware and the development of the backpropagation algorithm as well as recurrent neural networks and convolutional neural networks, renewed interest in ANNs. The 2010s, saw the development of a deep neural network (a neural network with many layers) called AlexNet. It greatly outperformed other image recognition models, and is thought to have launched the ongoing AI spring, and further increasing interest in ANNs. The transformer architecture was first described in 2017 as a method to teach ANNs grammatical dependencies in language, and is the predominant architecture used by large language models, such as GPT-4. Diffusion models were first described in 2015, and began to be used by image generation models such as DALL-E in the 2020s.

Perceptrons and other early neural networks

The simplest feedforward network consists of a single weight layer without activation functions. It would be just a linear map, and training it would be linear regression. Linear regression by least squares method was used by Legendre (1805) and Gauss (1795) for the prediction of planetary movement.Merriman, Mansfield. ''A List of Writings Relating to the Method of Least Squares: With Historical and Critical Notes''. Vol. 4. Academy, 1877.

Warren McCulloch and Walter Pitts (1943) considered a non-learning computational model for neural networks. This model paved the way for research to split into two approaches. One approach focused on biological processes while the other focused on the application of neural networks to artificial intelligence. This work led to work on nerve networks and their link to finite automata.

In the early 1940s, D. O. Hebb created a learning hypothesis based on the mechanism of neural plasticity that became known as Hebbian learning. Hebbian learning is unsupervised learning. This evolved into models for long-term potentiation. Researchers started applying these ideas to computational models in 1948 with Turing's B-type machines. Farley and Clark (1954) first used computational machines, then called "calculators", to simulate a Hebbian network. Other neural network computational machines were created by Rochester, Holland, Habit and Duda (1956).

Rosenblatt (1958) created the perceptron, an algorithm for pattern recognition. With mathematical notation, Rosenblatt described circuitry not in the basic perceptron, such as the exclusive-or circuit that could not be processed by neural networks at the time. In 1959, a biological model proposed by Nobel laureates Hubel and Wiesel was based on their discovery of two types of cells in the primary visual cortex: simple cells and complex cells.

Some say that research stagnated following Minsky and Papert '' Perceptrons'' (1969),.

Frank Rosenblatt (1958) proposed the perceptron, a multilayer perceptron (MLP) with 3 layers: an input layer, a hidden layer with randomized weights that did not learn, and an output layer. He later published a 1962 book also introduced variants and computer experiments, including a version with four-layer perceptrons where the last two layers have learned weights (and thus a proper multilayer perceptron). Some consider that the 1962 book developed and explored all of the basic ingredients of the deep learning systems of today.

Group method of data handling, a method to train arbitrarily deep neural networks was published by Alexey Ivakhnenko and Lapa in 1967, which they regarded as a form of polynomial regression, or a generalization of Rosenblatt's perceptron. A 1971 paper described a deep network with eight layers trained by this method.

The first deep learning multilayer perceptron trained by stochastic gradient descent was published in 1967 by Shun'ichi Amari. In computer experiments conducted by Amari's student Saito, a five layer MLP with two modifiable layers learned internal representations to classify non-linearily separable pattern classes. Subsequent developments in hardware and hyperparameter tunings have made end-to-end stochastic gradient descent the currently dominant training technique.

Backpropagation

Backpropagation is an efficient application of the chain rule derived by Gottfried Wilhelm Leibniz in 1673 to networks of differentiable nodes. The terminology "back-propagating errors" was actually introduced in 1962 by Rosenblatt, but he did not know how to implement this, although Henry J. Kelley had a continuous precursor of backpropagation in 1960 in the context of control theory. The modern form of backpropagation was developed multiple times in early 1970s. The earliest published instance was Seppo Linnainmaa's master thesis (1970). Paul Werbos developed it independently in 1971, but had difficulty publishing it until 1982. In 1986, David E. Rumelhart et al. popularized backpropagation.

Recurrent network architectures

One origin of RNN was statistical mechanics. The Ising model was developed by Wilhelm Lenz and Ernst Ising in the 1920s as a simple statistical mechanical model of magnets at equilibrium. Glauber in 1963 studied the Ising model evolving in time, as a process towards equilibrium (Glauber dynamics), adding in the component of time. Shun'ichi Amari in 1972 proposed to modify the weights of an Ising model by Hebbian learning rule as a model of associative memory, adding in the component of learning. This was popularized as the Hopfield network (1982).

Another origin of RNN was neuroscience. The word "recurrent" is used to describe loop-like structures in anatomy. In 1901, Cajal observed "recurrent semicircles" in the cerebellar cortex. In 1933, Lorente de Nó discovered "recurrent, reciprocal connections" by Golgi's method, and proposed that excitatory loops explain certain aspects of the vestibulo-ocular reflex. Hebb considered "reverberating circuit" as an explanation for short-term memory. The McCulloch and Pitts paper (1943) considered neural networks that contains cycles, and noted that the current activity of such networks can be affected by activity indefinitely far in the past.

Two early influential works were the Jordan network (1986) and the Elman network (1990), which applied RNN to study cognitive psychology. In 1993, a neural history compressor system solved a "Very Deep Learning" task that required more than 1000 subsequent layers in an RNN unfolded in time. Page 150 ff demonstrates credit assignment across the equivalent of 1,200 layers in an unfolded RNN.

LSTM

Sepp Hochreiter's diploma thesis (1991)S. Hochreiter.,
Untersuchungen zu dynamischen neuronalen Netzen
. . ''Diploma thesis. Institut f. Informatik, Technische Univ. Munich. Advisor: J. Schmidhuber'', 1991. proposed the neural history compressor, and identified and analyzed the vanishing gradient problem. In 1993, a neural history compressor system solved a "Very Deep Learning" task that required more than 1000 subsequent layers in an RNN unfolded in time. Page 150 ff demonstrates credit assignment across the equivalent of 1,200 layers in an unfolded RNN. Hochreiter proposed recurrent residual connections to solve the vanishing gradient problem. This led to the long short-term memory (LSTM), published in 1995. LSTM can learn "very deep learning" tasks with long credit assignment paths that require memories of events that happened thousands of discrete time steps before. That LSTM was not yet the modern architecture, which required a "forget gate", introduced in 1999, which became the standard RNN architecture.

Long short-term memory (LSTM) networks were invented by Hochreiter and Schmidhuber in 1995 and set accuracy records in multiple applications domains. It became the default choice for RNN architecture.

Around 2006, LSTM started to revolutionize speech recognition, outperforming traditional models in certain speech applications. LSTM also improved large-vocabulary speech recognition and text-to-speech synthesis and was used in Google voice search, and dictation on Android devices.

LSTM broke records for improved machine translation, language modeling and Multilingual Language Processing. LSTM combined with convolutional neural networks (CNNs) improved automatic image captioning.

Convolutional neural networks (CNNs)

The origin of the CNN architecture is the " neocognitron" introduced by Kunihiko Fukushima in 1980.
It was inspired by work of Hubel and Wiesel in the 1950s and 1960s which showed that cat visual cortices contain neurons that individually respond to small regions of the visual field.
The neocognitron introduced the two basic types of layers in CNNs: convolutional layers, and downsampling layers. A convolutional layer contains units whose receptive fields cover a patch of the previous layer. The weight vector (the set of adaptive parameters) of such a unit is often called a filter. Units can share filters. Downsampling layers contain units whose receptive fields cover patches of previous convolutional layers. Such a unit typically computes the average of the activations of the units in its patch. This downsampling helps to correctly classify objects in visual scenes even when the objects are shifted.

In 1969, Kunihiko Fukushima also introduced the ReLU (rectified linear unit) activation function. The rectifier has become the most popular activation function for CNNs and deep neural networks in general.

The time delay neural network (TDNN) was introduced in 1987 by Alex Waibel and was one of the first CNNs, as it achieved shift invariance. It did so by utilizing weight sharing in combination with backpropagation training. Alexander Waibel et al.,
Phoneme Recognition Using Time-Delay Neural Networks
' IEEE Transactions on Acoustics, Speech, and Signal Processing, Volume 37, No. 3, pp. 328. – 339 March 1989. Thus, while also using a pyramidal structure as in the neocognitron, it performed a global optimization of the weights instead of a local one.

In 1988, Wei Zhang et al. applied backpropagation to a CNN (a simplified Neocognitron with convolutional interconnections between the image feature layers and the last fully connected layer) for alphabet recognition. They also proposed an implementation of the CNN with an optical computing system.

In 1989, Yann LeCun et al. trained a CNN with the purpose of recognizing handwritten ZIP codes on mail. While the algorithm worked, training required 3 days.LeCun ''et al.'', "Backpropagation Applied to Handwritten Zip Code Recognition," ''Neural Computation'', 1, pp. 541–551, 1989. Learning was fully automatic, performed better than manual coefficient design, and was suited to a broader range of image recognition problems and image types.
Subsequently, Wei Zhang, et al. modified their model by removing the last fully connected layer and applied it for medical image object segmentation in 1991 and breast cancer detection in mammograms in 1994.

In 1990 Yamaguchi et al. introduced max-pooling, a fixed filtering operation that calculates and propagates the maximum value of a given region. They combined TDNNs with max-pooling in order to realize a speaker independent isolated word recognition system.
In a variant of the neocognitron called the cresceptron, instead of using Fukushima's spatial averaging, J. Weng et al. also used max-pooling where a downsampling unit computes the maximum of the activations of the units in its patch.J. Weng, N. Ahuja and T. S. Huang,
Cresceptron: a self-organizing neural network which grows adaptively
" ''Proc. International Joint Conference on Neural Networks'', Baltimore, Maryland, vol I, pp. 576–581, June, 1992.J. Weng, N. Ahuja and T. S. Huang,
Learning recognition and segmentation of 3-D objects from 2-D images
" ''Proc. 4th International Conf. Computer Vision'', Berlin, Germany, pp. 121–128, May, 1993.J. Weng, N. Ahuja and T. S. Huang,
Learning recognition and segmentation using the Cresceptron
" ''International Journal of Computer Vision'', vol. 25, no. 2, pp. 105–139, Nov. 1997. Max-pooling is often used in modern CNNs.

LeNet-5, a 7-level CNN by Yann LeCun et al. in 1998, that classifies digits, was applied by several banks to recognize hand-written numbers on checks () digitized in 32x32 pixel images. The ability to process higher-resolution images requires larger and more layers of CNNs, so this technique is constrained by the availability of computing resources.

In 2010, Backpropagation training through max-pooling was accelerated by GPUs and shown to perform better than other pooling variants.Dominik Scherer, Andreas C. Müller, and Sven Behnke:
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
" ''In 20th International Conference Artificial Neural Networks (ICANN)'', pp. 92–101, 2010. .
Behnke (2003) relied only on the sign of the gradient ( Rprop) on problems such as image reconstruction and face localization. Rprop is a first-order optimization algorithm created by Martin Riedmiller and Heinrich Braun in 1992.Martin Riedmiller und Heinrich Braun: Rprop – A Fast Adaptive Learning Algorithm. Proceedings of the International Symposium on Computer and Information Science VII, 1992

Deep learning

The deep learning revolution started around CNN- and GPU-based computer vision.

Although CNNs trained by backpropagation had been around for decades and GPU implementations of NNs for years, including CNNs, faster implementations of CNNs on GPUs were needed to progress on computer vision. Later, as deep learning becomes widespread, specialized hardware and algorithm optimizations were developed specifically for deep learning.

A key advance for the deep learning revolution was hardware advances, especially GPU. Some early work dated back to 2004. In 2009, Raina, Madhavan, and Andrew Ng reported a 100M deep belief network trained on 30 Nvidia GeForce GTX 280 GPUs, an early demonstration of GPU-based deep learning. They reported up to 70 times faster training.

In 2011, a CNN named ''DanNet'' by Dan Ciresan, Ueli Meier, Jonathan Masci, Luca Maria Gambardella, and Jürgen Schmidhuber achieved for the first time superhuman performance in a visual pattern recognition contest, outperforming traditional methods by a factor of 3. It then won more contests. They also showed showed how max-pooling CNNs on GPU improved performance significantly.

Many discoveries were empirical and focused on engineering. For example, in 2011, Xavier Glorot, Antoine Bordes and Yoshua Bengio found that the ReLU worked better than widely used activation functions prior to 2011.

In October 2012, AlexNet by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton won the large-scale ImageNet competition by a significant margin over shallow machine learning methods. Further incremental improvements included the VGG-16 network by Karen Simonyan and Andrew Zisserman and Google's Inceptionv3.

The success in image classification was then extended to the more challenging task of generating descriptions (captions) for images, often as a combination of CNNs and LSTMs....

In 2014, the state of the art was training “very deep neural network” with 20 to 30 layers. Stacking too many layers led to a steep reduction in training accuracy, known as the "degradation" problem. In 2015, two techniques were developed concurrently to train very deep networks: highway network and residual neural network (ResNet). The ResNet research team attempted to train deeper ones by empirically testing various tricks for training deeper networks until they discovered the deep residual network architecture.

Generative adversarial networks

In 1991, Juergen Schmidhuber published "artificial curiosity", neural networks in a zero-sum game. The first network is a generative model that models a probability distribution over output patterns. The second network learns by gradient descent to predict the reactions of the environment to these patterns. GANs can be regarded as a case where the environmental reaction is 1 or 0 depending on whether the first network's output is in a given set. It was extended to "predictability minimization" to create disentangled representations of input patterns''.''

Other people had similar ideas but did not develop them similarly. An idea involving adversarial networks was published in a 2010 blog post by Olli Niemitalo. This idea was never implemented and did not involve stochasticity in the generator and thus was not a generative model. It is now known as a conditional GAN or cGAN. An idea similar to GANs was used to model animal behavior by Li, Gauci and Gross in 2013.

Another inspiration for GANs was noise-contrastive estimation, which uses the same loss function as GANs and which Goodfellow studied during his PhD in 2010–2014.

Generative adversarial network (GAN) by (Ian Goodfellow et al., 2014) became state of the art in generative modeling during 2014-2018 period. Excellent image quality is achieved by Nvidia's StyleGAN (2018) based on the Progressive GAN by Tero Karras et al. Here the GAN generator is grown from small to large scale in a pyramidal fashion. Image generation by GAN reached popular success, and provoked discussions concerning deepfakes. Diffusion models (2015) eclipsed GANs in generative modeling since then, with systems such as DALL·E 2 (2022) and Stable Diffusion (2022).

Attention mechanism and Transformer

The human selective attention had been studied in neuroscience and cognitive psychology. Selective attention of audition was studied in the cocktail party effect (Colin Cherry, 1953). ( Donald Broadbent, 1958) proposed the filter model of attention. Selective attention of vision was studied in the 1960s by George Sperling's partial report paradigm. It was also noticed that saccade control is modulated by cognitive processes, in that the eye moves preferentially towards areas of high salience. As the fovea of the eye is small, the eye cannot sharply resolve all of the visual field at once. The use of saccade control allows the eye to quickly scan important features of a scene.

These researches inspired algorithms, such as a variant of the Neocognitron. Conversely, developments in neural networks had inspired circuit models of biological visual attention.

A key aspect of attention mechanism is the use of multiplicative operations, which had been studied under the names of '' higher-order neural networks'', ''multiplication units'', ''sigma-pi units'', ''fast weight controllers'', and ''hyper-networks''.

Recurrent attention

During the deep learning era, attention mechanism was developed solve similar problems in encoding-decoding.

The idea of encoder-decoder sequence transduction had been developed in the early 2010s. The papers most commonly cited as the originators that produced seq2seq are two papers from 2014. A seq2seq architecture employs two RNN, typically LSTM, an "encoder" and a "decoder", for sequence transduction, such as machine translation. They became state of the art in machine translation, and was instrumental in the development of attention mechanism and Transformer.

An image captioning model was proposed in 2015, citing inspiration from the seq2seq model. that would encode an input image into a fixed-length vector. (Xu et al 2015), citing (Bahdanau et al 2014), applied the attention mechanism as used in the seq2seq model to image captioning.

Transformer

One problem with seq2seq models was their use of recurrent neural networks, which are not parallelizable as both the encoder and the decoder processes the sequence token-by-token. The ''decomposable attention'' attempted to solve this problem by processing the input sequence in parallel, before computing a "soft alignment matrix" ("alignment" is the terminology used by (Bahdanau et al 2014)). This allowed parallel processing.

The idea of using attention mechanism for self-attention, instead of in an encoder-decoder (cross-attention), was also proposed during this period, such as in differentiable neural computers and neural Turing machines. It was termed ''intra-attention'' where an LSTM is augmented with a memory network as it encodes an input sequence.

These strands of development were combined in the Transformer architecture, published in '' Attention Is All You Need'' (2017). Subsequently, attention mechanisms were extended within the framework of Transformer architecture.

Seq2seq models with attention still suffered from the same issue with recurrent networks, which is that they are hard to parallelize, which prevented them to be accelerated on GPUs. In 2016, ''decomposable attention'' applied attention mechanism to the feedforward network, which are easy to parallelize. One of its authors, Jakob Uszkoreit, suspected that attention ''without'' recurrence is sufficient for language translation, thus the title "attention is ''all'' you need".

In 2017, the original (100M-sized) encoder-decoder transformer model was proposed in the " Attention is all you need" paper. At the time, the focus of the research was on improving seq2seq for machine translation, by removing its recurrence to processes all tokens in parallel, but preserving its dot-product attention mechanism to keep its text processing performance. Its parallelizability was an important factor to its widespread use in large neural networks.

Unsupervised and self-supervised learning

Self-organizing maps

Self-organizing maps (SOMs) were described by Teuvo Kohonen in 1982. SOMs are neurophysiologically inspired artificial neural networks that learn low-dimensional representations of high-dimensional data while preserving the topological structure of the data. They are trained using competitive learning.

SOMs create internal representations reminiscent of the cortical homunculus, a distorted representation of the human body, based on a neurological "map" of the areas and proportions of the human brain dedicated to processing sensory functions, for different parts of the body.

Boltzmann machines

During 1985–1995, inspired by statistical mechanics, several architectures and methods were developed by Terry Sejnowski, Peter Dayan, Geoffrey Hinton, etc., including the Boltzmann machine, restricted Boltzmann machine, Helmholtz machine, and the wake-sleep algorithm. These were designed for unsupervised learning of deep generative models. However, those were more computationally expensive compared to backpropagation. Boltzmann machine learning algorithm, published in 1985, was briefly popular before being eclipsed by the backpropagation algorithm in 1986. (p. 112 ).

Geoffrey Hinton et al. (2006) proposed learning a high-level internal representation using successive layers of binary or real-valued latent variables with a restricted Boltzmann machine to model each layer. This RBM is a generative stochastic feedforward neural network that can learn a probability distribution over its set of inputs. Once sufficiently many layers have been learned, the deep architecture may be used as a generative model by reproducing the data when sampling down the model (an "ancestral pass") from the top level feature activations.

Deep learning

In 2012, Andrew Ng and Jeff Dean created an FNN that learned to recognize higher-level concepts, such as cats, only from watching unlabeled images taken from YouTube videos.

Other aspects

Knowledge distillation

Knowledge distillation or model distillation is the process of transferring knowledge from a large model to a smaller one. The idea of using the output of one neural network to train another neural network was studied as the teacher-student network configuration. In 1992, several papers studied the statistical mechanics of teacher-student network configuration, where both networks are committee machines or both are parity machines.

Another early example of network distillation was also published in 1992, in the field of recurrent neural networks (RNNs). The problem was sequence prediction. It was solved by two RNNs. One of them ("atomizer") predicted the sequence, and another ("chunker") predicted the errors of the atomizer. Simultaneously, the atomizer predicted the internal states of the chunker. After the atomizer manages to predict the chunker's internal states well, it would start fixing the errors, and soon the chunker is obsoleted, leaving just one RNN in the end.

A related methodology was ''model compression'' or ''pruning'', where a trained network is reduced in size. It was inspired by neurobiological studies showing that the human brain is resistant to damage, and was studied in the 1980s, via methods such as Biased Weight Decay and Optimal Brain Damage.

Hardware-based designs

The development of metal–oxide–semiconductor (MOS) very-large-scale integration (VLSI), combining millions or billions of MOS transistors onto a single chip in the form of complementary MOS (CMOS) technology, enabled the development of practical artificial neural networks in the 1980s.

Computational devices were created in CMOS, for both biophysical simulation and neuromorphic computing inspired by the structure and function of the human brain. Nanodevices for very large scale principal components analyses and convolution may create a new class of neural computing because they are fundamentally analog rather than digital (even though the first implementations may use digital devices).

Notes

References

External links

* {{Cite web, url=https://drive.google.com/file/d/1f0sPHv7ozHafASPwIOfuvF_RvP3FDPY0, title=Lecun 2019-7-11 ACM Tech Talk, website=Google Docs, access-date=2020-02-13

Computational statistics

Computational neuroscience