AI News, Inside AI artificial intelligence

Radboud Center for Artificial Intelligence

Inspired by the human brain and for over 30 years, Radboud University is a global frontrunner on research about innovative intelligent learning systems.

Inside AI ebook: Artificial intelligence in the enterprise

Artificial intelligence is fueling enormous change in business, allowing for more accurate predictive analytics than ever before, so-called autonomous data-center systems and new services in areas like finance, customer relations and healthcare.

Adding to the confusion, AI comprises concepts and terms that overlap and create misunderstanding about the field AI is a blanket term for various algorithms, methodologies and technologies that, broadly speaking, allow software to accomplish tasks that historically were associated with human intelligence, such as responding to natural language queries, recognizing images and sounds, making decisions and predictions.

There are pre-built APIs you can incorporate into your own systems, cloud-based machine learning offerings for building data models and a wide range of programming tools you can use to build AI applications from the ground up.

Artificial neural network

Artificial neural networks (ANN) or connectionist systems are computing systems that are inspired by, but not identical to, biological neural networks that constitute animal brains.

For example, in image recognition, they might learn to identify images that contain cats by analyzing example images that have been manually labeled as 'cat' or 'no cat' and using the results to identify cats in other images.

An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain.

In ANN implementations, the 'signal' at a connection is a real number, and the output of each neuron is computed by some non-linear function of the sum of its inputs.

Signals travel from the first layer (the input layer), to the last layer (the output layer), possibly after traversing the layers multiple times.

ANNs have been used on a variety of tasks, including computer vision, speech recognition, machine translation, social network filtering, playing board and video games, medical diagnosis and even in activities that have traditionally been considered as reserved to humans, like painting[1]

In 1970, Linnainmaa published the general method for automatic differentiation (AD) of discrete connected networks of nested differentiable functions.[16][17]

Werbos's (1975) backpropagation algorithm enabled practical training of multi-layer networks.In 1982, he applied Linnainmaa's AD method to neural networks in the way that became widely used.[11][19]

who discovered that basic perceptrons were incapable of processing the exclusive-or circuit and that computers lacked sufficient power to process useful neural networks.

In 1992, max-pooling was introduced to help with least shift invariance and tolerance to deformation to aid in 3D object recognition.[21][22][23]

Schmidhuber adopted a multi-level hierarchy of networks (1992) pre-trained one level at a time by unsupervised learning and fine-tuned by backpropagation.[24]

(2006) proposed learning a high-level representation using successive layers of binary or real-valued latent variables with a restricted Boltzmann machine[25]

In 2012, Ng and Dean created a network that learned to recognize higher-level concepts, such as cats, only from watching unlabeled images.[26]

Unsupervised pre-training and increased computing power from GPUs and distributed computing allowed the use of larger networks, particularly in image and visual recognition problems, which became known as 'deep learning'.[citation needed]

showed that despite the vanishing gradient problem, GPUs make backpropagation feasible for many-layered feedforward neural networks.[28]

Between 2009 and 2012, ANNs began winning prizes in ANN contests, approaching human level performance on various tasks, initially in pattern recognition and machine learning.[29][30]

won three competitions in connected handwriting recognition in 2009 without any prior knowledge about the three languages to be learned.[33][32]

ANNs began as an attempt to exploit the architecture of the human brain to perform tasks that conventional algorithms had had little success.

They soon reoriented towards improving empirical results, mostly abandoning attempts to remain true to their biological precursors.

ANNs retained the biological concept of artificial neurons, which receive input, combine the input with their internal state (activation) and an optional threshold using an activation function, and produce output using an output function.

The propagation function computes the input to a neuron from the outputs of its predecessor neurons and their connections as a weighted sum.[36]

They can be pooling, where a group of neurons in one layer connect to a single neuron in the next layer, thereby reducing the number of neurons in that layer.[40]

The outputs are actually numbers, so when the error is low, the difference between the output (almost certainly a cat) and the correct answer (cat) is small.

The learning rate defines the size of the corrective steps that the model takes to adjust for errors in each observation.

A high learning rate shortens the training time, but with lower ultimate accuracy, while a lower learning rate takes longer, but with the potential for greater accuracy.

In order to avoid oscillation inside the network such as alternating connection weights, and to improve the rate of convergence, refinements use an adaptive learning rate that increases or decreases as appropriate.[44]

The concept of momentum allows the balance between the gradient and the previous change to be weighted such that the weight adjustment depends to some degree on the previous change.

While it is possible to define a cost function ad hoc, frequently the choice is determined by the functions desirable properties (such as convexity) or because it arises from the model (e.g., in a probabilistic model the model's posterior probability can be used as an inverse cost).

Technically, backprop calculates the gradient (the derivative) of the cost function associated with a given state with respect to the weights.

A commonly used cost is the mean-squared error, which tries to minimize the average squared error between the network's output and the desired output.

Tasks suited for supervised learning are pattern recognition (also known as classification) and regression (also known as function approximation).

This can be thought of as learning with a 'teacher', in the form of a function that provides continuous feedback on the quality of solutions obtained thus far.

The cost function is dependent on the task (the model domain) and any a priori assumptions (the implicit properties of the model, its parameters and the observed variables).

whereas in statistical modeling, it could be related to the posterior probability of the model given the data (note that in both of those examples those quantities would be maximized rather than minimized).

In applications such as playing video games, an actor takes a string of actions, receiving a generally unpredictable response from the environment after each one.

In reinforcement learning, the aim is to weight the network (devise a policy) to perform actions that minimize long-term (expected cumulative) cost.

at each point in time the agent performs an action and the environment generates an observation and an instantaneous cost, according to some (usually unknown) rules.

At any juncture, the agent decides whether to explore new actions to uncover their costs or to exploit prior learning to proceed more quickly.

Because the state transitions are not known, probability distributions are used instead: the instantaneous cost distribution

because of ANNs ability to mitigate losses of accuracy even when reducing the discretization grid density for numerically approximating the solution of control problems.

However, batch learning typically yields a faster, more stable descent to a local minimum, since each update is performed in the direction of the batch's average error.

A common compromise is to use 'mini-batches', small batches with samples in each batch selected stochastically from the entire data set.

The simplest types have one or more static components, including number of units, number of layers, unit weights and topology.

Some of the main breakthroughs include: convolutional neural networks that have proven particularly successful in processing visual and other two-dimensional data;[64][65]

competitive networks such as generative adversarial networks in which multiple networks (of varying structure) compete with each other, on tasks such as winning a game[72]

The basic search algorithm is to propose a candidate model, evaluate it against a dataset and use the results as feedback to teach the NAS network.[74]

Design issues include deciding the number, type and connectedness of network layers, as well as the size of each and the connection type (full, pooling, ...).

Hyperparameters must also be defined as part of the design (they are not learned), governing matters such as how many neurons are in each layer, learning rate, step, stride, depth, receptive field and padding (for CNNs), etc.[76]

object recognition and more), sequence recognition (gesture, speech, handwritten and printed text recognition), medical diagnosis, finance[82]

and to distinguish highly invasive cancer cell lines from less invasive lines using only cell shape information.[86][87]

the dynamics of neural circuitry arise from interactions between individual neurons and how behavior can arise from abstract neural modules that represent complete subsystems.

Studies considered long-and short-term plasticity of neural systems and their relation to learning and memory from the individual neuron to the system level.

specific recurrent architecture with rational-valued weights (as opposed to full precision real number-valued weights) has the power of a universal Turing machine,[107]

This concept emerges in a probabilistic (Bayesian) framework, where regularization can be performed by selecting a larger prior probability over simpler models;

but also in statistical learning theory, where the goal is to minimize over two quantities: the 'empirical risk' and the 'structural risk', which roughly corresponds to the error over the training set and the predicted error in unseen data due to overfitting.

Supervised neural networks that use a mean squared error (MSE) cost function can use formal statistical methods to determine the confidence of the trained model.

A confidence analysis made this way is statistically valid as long as the output probability distribution stays the same and the network is not modified.

By assigning a softmax activation function, a generalization of the logistic function, on the output layer of the neural network (or a softmax component in a component-based network) for categorical target variables, the outputs can be interpreted as posterior probabilities.

Potential solutions include randomly shuffling training examples, by using a numerical optimization algorithm that does not take too large steps when changing the network connections following an example, grouping examples in so-called mini-batches and/or introducing a recursive least squares algorithm for CMAC.[62]

Sensor neurons fire action potentials more frequently with sensor activation and muscle cells pull more strongly when their associated motor neurons receive action potentials more frequently.[110]

Other than the case of relaying information from a sensor neuron to a motor neuron, almost nothing of the principles of how information is handled by biological neural networks is known.

This allows simple statistical association (the basic function of artificial neural networks) to be described as learning or recognition.

Alexander Dewdney commented that, as a result, artificial neural networks have a 'something-for-nothing quality, one that imparts a peculiar aura of laziness and a distinct lack of curiosity about just how good these computing systems are.

Neural networks, for instance, are in the dock not only because they have been hyped to high heaven, (what hasn't?) but also because you could create a successful net without understanding how it worked: the bunch of numbers that captures its behaviour would in all probability be 'an opaque, unreadable table...valueless as a scientific resource'.

In spite of his emphatic declaration that science is not technology, Dewdney seems here to pillory neural nets as bad science when most of those devising them are just trying to be good engineers.

argued that the brain self-wires largely according to signal statistics and therefore, a serial cascade cannot catch all major statistical dependencies.

While the brain has hardware tailored to the task of processing signals through a graph of neurons, simulating even a simplified neuron on von Neumann architecture may consume vast amounts of memory and storage.

Schmidhuber noted that the resurgence of neural networks in the twenty-first century is largely attributable to advances in hardware: from 1991 to 2015, computing power, especially as delivered by GPGPUs (on GPUs), has increased around a million-fold, making the standard backpropagation algorithm feasible for training networks that are several layers deeper than before.[117]

Neuromorphic engineering addresses the hardware difficulty directly, by constructing non-von-Neumann chips to directly implement neural networks in circuitry.

Furthermore, researchers involved in exploring learning algorithms for neural networks are gradually uncovering general principles that allow a learning machine to be successful.

Advocates of hybrid models (combining neural networks and symbolic approaches), claim that such a mixture can better capture the mechanisms of the human mind.[121][122]

AI cannot be deployed in isolation; it needs Architecture

AI cannot be deployed in isolation. Recently, Andrew Ng, one of the foremost Artificial Intelligence researchers who also built the AI teams at Google and Baidu ...

China's rise in artificial intelligence | CNBC Reports

China's vast amount of data is helping advance its artificial intelligence research. CNBC's Uptin Saiidi speaks to experts VC Kai-Fu Lee, author Thomas ...

The Future of Your Job in the Age of AI | Robots & Us | WIRED

Robot co-workers and artificial intelligence assistants are becoming more common in the workplace. Could they edge human employees out? What then?

The Rise of Artificial Intelligence | Documentary HD

AI (artificial intelligence) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the ...

Why AI Will DESTROY Us All - How ARTIFICIAL INTELLIGENCE Will Summon The Demon (2019)

Welcome to Open Your Reality. In this video, I'm going to talk about why artificial intelligence will destroy us all. Why do I say that? Because AI danger to ...

Amazon is using AI in almost everything it does

CNN's Rachel Crane goes inside Amazon HQ to see how Amazon uses AI to improve customer experiences, from cashier-less stores to Alexa's new tricks.

Most AMAZING Examples Of Artificial Intelligence! (AI)

Check out the Most AMAZING Examples Of Artificial Intelligence (AI)! From deep learning sophisticated robots to machine learning computers, this top 10 list of ...

Google's DeepMind AI Just Taught Itself To Walk

Google's artificial intelligence company, DeepMind, has developed an AI that has managed to learn how to walk, run, jump, and climb without any prior guidance ...

This Freaky Baby Could Be the Future of AI. Watch It in Action

Mar. 23 -- Mark Sagar started his career by building medical simulations of body parts. He took those skills and went into CGI, most famously for movies ...

How artificial intelligence will change your world in 2019, for better or worse

From a science fiction dream to a critical part of our everyday lives, artificial intelligence is everywhere. You probably don't see AI at work, and that's by design.