AI News, BOOK REVIEW: Aspects Of Artificial Intelligence artificial intelligence
 On 24. december 2018
 By Read More
The WEIRD Aspects of Artificial Intelligence
In her talk she explained that data is the fuel, and the algorithm is the engine in creating an AI model.
A problem statement or key objective is identified and then a series of steps are taken: data collection, data analysis, data packaging, testing and benchmarking, deployment, learning, and a continuous cycle of refining and improving.
The source of bias could be in the data—either the training data that determines how AI learns to aggregate data, or in the test data used for evaluating the aggregated data.
 On 24. december 2018
 By Read More
Artificial Intelligence and the coming of the selfdesigning machine
Manufacturing is in the early stages of a state of disruption brought on by technologies such as artificial intelligence (AI) and 3D printing. 'Additive manufacturing' has already worked itself into companies such as Porsche and Bugatti, and aircraft builder Airbus is experimenting with UAV THOR, a drone made entirely of 3Dprinted parts.
“In an AIdriven generative design paradigm, humans input design goals and material parameters,” explains Avi Reichental, the CEO and founder of XponentialWorks (a venture investment, corporate advisory, and product development company specializing in artificial intelligence, 3D printing, robotics, and digital transformation).
This includes designs that are stronger, lighter and use less material than would be used otherwise to save money, increase scalability, and raise efficiency while enhancing form and function.” In this increasingly connected manufacturing chain, a product’s form and features don't even need to be finished when it ships.
“For example, a robot on Mars might detect very loose sand and determine it cannot move about efficiently to complete its mission,” explains Ben Schrauwen, cofounder and CTO of Oqton, an autonomous manufacturing platform. “The robot could learn to suggest different modalities on how to move in that environment, and, with 3D printing technology and some local robotics, it's very conceivable that the robot could reconfigure itself at a distance to continue its mission unimpeded.” Interplanetary travel and space missions aside, there is plenty of motivation to enable things to codesign or selfdesign here on Earth, too.
“The most exciting change is the embedding of sensors within manufactured items to create a design system that is a selfimproving circuit, where the sensors provide feedback to the design to cause it to respond and improve,” said Tod Northman, partner at Tucker Ellis, a law firm with a specialized practice in intellectual property and liability issues concerning autonomous vehicles and other artificially intelligent devices. “Such a system will become a selfimproving loop, with better products resulting without human intervention.'
 On 24. december 2018
 By Read More
Artificial neural network
Artificial Neural Networks (ANN) or connectionist systems are computing systems vaguely inspired by the biological neural networks that constitute animal brains.[1]
The neural network itself is not an algorithm, but rather a framework for many different machine learning algorithms to work together and process complex data inputs.[2]
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.
An artificial neuron that receives a signal can process it and then signal additional artificial neurons connected to it.
In common ANN implementations, the signal at a connection between artificial neurons is a real number, and the output of each artificial neuron is computed by some nonlinear 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.
Artificial neural networks have been used on a variety of tasks, including computer vision, speech recognition, machine translation, social network filtering, playing board and video games and medical diagnosis.
(1943) created a computational model for neural networks based on mathematics and algorithms called threshold logic.
One approach focused on biological processes in the brain while the other focused on the application of neural networks to artificial intelligence.
With mathematical notation, Rosenblatt described circuitry not in the basic perceptron, such as the exclusiveor circuit that could not be processed by neural networks at the time.[9]
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.[10]
The second was that computers didn't have enough processing power to effectively handle the work required by large neural networks.
Much of artificial intelligence had focused on highlevel (symbolic) models that are processed by using algorithms, characterized for example by expert systems with knowledge embodied in ifthen rules, until in the late 1980s research expanded to lowlevel (subsymbolic) machine learning, characterized by knowledge embodied in the parameters of a cognitive model.[citation needed]
key trigger for renewed interest in neural networks and learning was Werbos's (1975) backpropagation algorithm that effectively solved the exclusiveor problem by making the training of multilayer networks feasible and efficient.
Support vector machines and other, much simpler methods such as linear classifiers gradually overtook neural networks in machine learning popularity.
The vanishing gradient problem affects manylayered feedforward networks that used backpropagation and also recurrent neural networks (RNNs).[22][23]
As errors propagate from layer to layer, they shrink exponentially with the number of layers, impeding the tuning of neuron weights that is based on those errors, particularly affecting deep networks.
To overcome this problem, Schmidhuber adopted a multilevel hierarchy of networks (1992) pretrained one level at a time by unsupervised learning and finetuned by backpropagation.[24]
(2006) proposed learning a highlevel representation using successive layers of binary or realvalued latent variables with a restricted Boltzmann machine[26]
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.[27][28]
In 2012, Ng and Dean created a network that learned to recognize higherlevel concepts, such as cats, only from watching unlabeled images taken from YouTube videos.[29]
Earlier challenges in training deep neural networks were successfully addressed with methods such as unsupervised pretraining, while available computing power increased through the use of GPUs and distributed computing.
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).[31]
in Schmidhuber's group showed that despite the vanishing gradient problem, GPUs makes backpropagation feasible for manylayered feedforward neural networks.
Between 2009 and 2012, recurrent neural networks and deep feedforward neural networks developed in Schmidhuber's research group won eight international competitions in pattern recognition and machine learning.[33][34]
won three competitions in connected handwriting recognition at the 2009 International Conference on Document Analysis and Recognition (ICDAR), without any prior knowledge about the three languages to be learned.[37][36]
Researchers demonstrated (2010) that deep neural networks interfaced to a hidden Markov model with contextdependent states that define the neural network output layer can drastically reduce errors in largevocabulary speech recognition tasks such as voice search.
A team from his lab won a 2012 contest sponsored by Merck to design software to help find molecules that might identify new drugs.[47]
As of 2011[update], the state of the art in deep learning feedforward networks alternated between convolutional layers and maxpooling layers,[42][48]
Artificial neural networks were able to guarantee shift invariance to deal with small and large natural objects in large cluttered scenes, only when invariance extended beyond shift, to all ANNlearned concepts, such as location, type (object class label), scale, lighting and others.
An artificial neural network is a network of simple elements called artificial neurons, which receive input, change their internal state (activation) according to that input, and produce output depending on the input and activation.
An artificial neuron mimics the working of a biophysical neuron with inputs and outputs, but is not a biological neuron model.
The network forms by connecting the output of certain neurons to the input of other neurons forming a directed, weighted graph.
The weights as well as the functions that compute the activation can be modified by a process called learning which is governed by a learning rule.[52]
j
i
j
Sometimes a bias term added to total weighted sum of inputs to serve as threshold to shift the activation function.[53]
j
i
The learning rule is a rule or an algorithm which modifies the parameters of the neural network, in order for a given input to the network to produce a favored output.
A common use of the phrase 'ANN model' is really the definition of a class of such functions (where members of the class are obtained by varying parameters, connection weights, or specifics of the architecture such as the number of neurons or their connectivity).
g
i
(
∑
i
w
i
g
i
(
x
)
)
(commonly referred to as the activation function[55]) is some predefined function, such as the hyperbolic tangent or sigmoid function or softmax function or rectifier function.
g
i
g
1
g
2
g
n
f
∗
R
f
∗
f
∗
is an important concept in learning, as it is a measure of how far away a particular solution is from an optimal solution to the problem to be solved.
For applications where the solution is data dependent, the cost must necessarily be a function of the observations, otherwise the model would not relate to the data.
[
(
f
(
x
)
−
y
)
2
]
D
D
C
^
1
N
∑
i
=
1
N
x
i
y
i
)
2
D
In neural network methods, some form of online machine learning is frequently used for finite datasets.
While it is possible to define an ad hoc cost function, frequently a particular cost function is used, either because it has desirable properties (such as convexity) or because it arises naturally from a particular formulation of the problem (e.g., in a probabilistic formulation the posterior probability of the model can be used as an inverse cost).
Backpropagation is a method to calculate the gradient of the loss function (produces the cost associated with a given state) with respect to the weights in an ANN.
In 1970, Linnainmaa finally published the general method for automatic differentiation (AD) of discrete connected networks of nested differentiable functions.[64][65]
In 1986, Rumelhart, Hinton and Williams noted that this method can generate useful internal representations of incoming data in hidden layers of neural networks.[71]
The choice of the cost function depends on factors such as the learning type (supervised, unsupervised, reinforcement, etc.) and the activation function.
For example, when performing supervised learning on a multiclass classification problem, common choices for the activation function and cost function are the softmax function and cross entropy function, respectively.
j
exp
⁡
(
x
j
)
∑
k
exp
⁡
(
x
k
)
j
j
k
j
j
j
j
j
The model consists of multiple layers, each of which has a rectified linear unit as its activation function for nonlinear transformation.
The network is trained to minimize L2 error for predicting the mask ranging over the entire training set containing bounding boxes represented as masks.
the cost function is related to the mismatch between our mapping and the data and it implicitly contains prior knowledge about the problem domain.[79]
commonly used cost is the meansquared error, which tries to minimize the average squared error between the network's output,
Minimizing this cost using gradient descent for the class of neural networks called multilayer perceptrons (MLP), produces the backpropagation algorithm for training neural networks.
Tasks that fall within the paradigm of supervised learning are pattern recognition (also known as classification) and regression (also known as function approximation).
The supervised learning paradigm is also applicable to sequential data (e.g., for hand writing, speech and gesture recognition).
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).
)
2
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).
y
t
x
t
c
t
The aim is to discover a policy for selecting actions that minimizes some measure of a longterm cost, e.g., the expected cumulative cost.
s
1
,
.
.
.
,
s
n
a
1
,
.
.
.
,
a
m
c
t

s
t
x
t

s
t
s
t
+
1

s
t
a
t
because of the ability of Artificial neural networks to mitigate losses of accuracy even when reducing the discretization grid density for numerically approximating the solution of the original control problems.
Tasks that fall within the paradigm of reinforcement learning are control problems, games and other sequential decision making tasks.
Training a neural network model essentially means selecting one model from the set of allowed models (or, in a Bayesian framework, determining a distribution over the set of allowed models) that minimizes the cost.
This is done by simply taking the derivative of the cost function with respect to the network parameters and then changing those parameters in a gradientrelated direction.
When an input vector is presented to the network, it is propagated forward through the network, layer by layer, until it reaches the output layer.
The error values are then propagated from the output back through the network, until each neuron has an associated error value that reflects its contribution to the original output.
In the second phase, this gradient is fed to the optimization method, which in turn uses it to update the weights, in an attempt to minimize the loss function.
1
2
R
m
1
2
R
n
0
1
2
R
e
N
1
1
p
p
0
1
p
0
i
i
i
i
−
1
p
N
p
1
1
1
0
N
1
1
0
1

2
The lines labeled 'backward pass' can be implemented using the backpropagation algorithm, which calculates the gradient of the error of the network regarding the network's modifiable weights.[94]
is important, since a high value can cause too strong a change, causing the minimum to be missed, while a too low learning rate slows the training unnecessarily.
In order to avoid oscillation inside the network such as alternating connection weights, and to improve the rate of convergence, refinements of this algorithm use an adaptive learning rate.[95]
Similar to a ball rolling down a mountain, whose current speed is determined not only by the current slope of the mountain but also by its own inertia, inertia can be added:
i
j
j
i
i
j
depend both on the current gradient of the error function (slope of the mountain, 1st summand), as well as on the weight change from the previous point in time (inertia, 2nd summand).
Since, for example, the gradient of the error function becomes very small in flat plateaus, a plateau would immediately lead to a 'deceleration' of the gradient descent.
Stochastic learning introduces 'noise' into the gradient descent process, using the local gradient calculated from one data point;
However, batch learning typically yields a faster, more stable descent to a local minimum, since each update is performed in the direction of the average error of the batch.
A common compromise choice is to use 'minibatches', meaning small batches and with samples in each batch selected stochastically from the entire data set.
convolutional neural network (CNN) is a class of deep, feedforward networks, composed of one or more convolutional layers with fully connected layers (matching those in typical Artificial neural networks) on top.
recent development has been that of Capsule Neural Network (CapsNet), the idea behind which is to add structures called capsules to a CNN and to reuse output from several of those capsules to form more stable (with respect to various perturbations) representations for higher order capsules.[105]
can find an RNN weight matrix that maximizes the probability of the label sequences in a training set, given the corresponding input sequences.
provide a framework for efficiently trained models for hierarchical processing of temporal data, while enabling the investigation of the inherent role of RNN layered composition.[clarification needed]
This is particularly helpful when training data are limited, because poorly initialized weights can significantly hinder model performance.
that integrate the various and usually different filters (preprocessing functions) into its many layers and to dynamically rank the significance of the various layers and functions relative to a given learning task.
This grossly imitates biological learning which integrates various preprocessors (cochlea, retina, etc.) and cortexes (auditory, visual, etc.) and their various regions.
Its deep learning capability is further enhanced by using inhibition, correlation and its ability to cope with incomplete data, or 'lost' neurons or layers even amidst a task.
The linkweights allow dynamic determination of innovation and redundancy, and facilitate the ranking of layers, of filters or of individual neurons relative to a task.
LAMSTAR had a much faster learning speed and somewhat lower error rate than a CNN based on ReLUfunction filters and max pooling, in 20 comparative studies.[142]
These applications demonstrate delving into aspects of the data that are hidden from shallow learning networks and the human senses, such as in the cases of predicting onset of sleep apnea events,[134]
The whole process of auto encoding is to compare this reconstructed input to the original and try to minimize the error to make the reconstructed value as close as possible to the original.
with a specific approach to good representation, 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.
x
~
x
~
x
~
x
~
x
~
of the first denoising auto encoder is learned and used to uncorrupt the input (corrupted input), the second level can be trained.[148]
Once the stacked auto encoder is trained, its output can be used as the input to a supervised learning algorithm such as support vector machine classifier or a multiclass logistic regression.[148]
It formulates the learning as a convex optimization problem with a closedform solution, emphasizing the mechanism's similarity to stacked generalization.[152]
Each block estimates the same final label class y, and its estimate is concatenated with original input X to form the expanded input for the next block.
Thus, the input to the first block contains the original data only, while downstream blocks' input adds the output of preceding blocks.
It offers two important improvements: it uses higherorder information from covariance statistics, and it transforms the nonconvex problem of a lowerlayer to a convex subproblem of an upperlayer.[154]
TDSNs use covariance statistics in a bilinear mapping from each of two distinct sets of hidden units in the same layer to predictions, via a thirdorder tensor.
The need for deep learning with realvalued inputs, as in Gaussian restricted Boltzmann machines, led to the spikeandslab RBM (ssRBM), which models continuousvalued inputs with strictly binary latent variables.[158]
One of these terms enables the model to form a conditional distribution of the spike variables by marginalizing out the slab variables given an observation.
However, these architectures are poor at learning novel classes with few examples, because all network units are involved in representing the input (a distributed representation) and must be adjusted together (high degree of freedom).
It is a full generative model, generalized from abstract concepts flowing through the layers of the model, which is able to synthesize new examples in novel classes that look 'reasonably' natural.
h
(
1
)
h
(
2
)
h
(
3
)
(
1
)
(
2
)
(
3
)
1
2
3
1
2
3
3
1
2
3
3
deep predictive coding network (DPCN) is a predictive coding scheme that uses topdown information to empirically adjust the priors needed for a bottomup inference procedure by means of a deep, locally connected, generative model.
DPCNs predict the representation of the layer, by using a topdown approach using the information in upper layer and temporal dependencies from previous states.[176]
For example, in sparse distributed memory or hierarchical temporal memory, the patterns encoded by neural networks are used as addresses for contentaddressable memory, with 'neurons' essentially serving as address encoders and decoders.
Preliminary results demonstrate that neural Turing machines can infer simple algorithms such as copying, sorting and associative recall from input and output examples.
Approaches that represent previous experiences directly and use a similar experience to form a local model are often called nearest neighbour or knearest neighbors methods.[191]
Unlike sparse distributed memory that operates on 1000bit addresses, semantic hashing works on 32 or 64bit addresses found in a conventional computer architecture.
These models have been applied in the context of question answering (QA) where the longterm memory effectively acts as a (dynamic) knowledge base and the output is a textual response.[196]
While training extremely deep (e.g., 1 million layers) neural networks might not be practical, CPUlike architectures such as pointer networks[198]
overcome this limitation by using external randomaccess memory and other components that typically belong to a computer architecture such as registers, ALU and pointers.
The key characteristic of these models is that their depth, the size of their shortterm memory, and the number of parameters can be altered independently – unlike models like LSTM, whose number of parameters grows quadratically with memory size.
In that work, an LSTM RNN or CNN was used as an encoder to summarize a source sentence, and the summary was decoded using a conditional RNN language model to produce the translation.[203]
Multilayer kernel machines (MKM) are a way of learning highly nonlinear functions by iterative application of weakly nonlinear kernels.
l
For the sake of dimensionality reduction of the updated representation in each layer, a supervised strategy selects the best informative features among features extracted by KPCA.
The main idea is to use a kernel machine to approximate a shallow neural net with an infinite number of hidden units, then use stacking to splice the output of the kernel machine and the raw input in building the next, higher level of the kernel machine.
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.[207]
Because of their ability to reproduce and model nonlinear processes, Artificial neural networks have found many applications in a wide range of disciplines.
gameplaying and decision making (backgammon, chess, poker), pattern recognition (radar systems, face identification, signal classification,[210]
object recognition and more), sequence recognition (gesture, speech, handwritten and printed text recognition), medical diagnosis, finance[211]
and to distinguish highly invasive cancer cell lines from less invasive lines using only cell shape information.[215][216]
models of how the dynamics of neural circuitry arise from interactions between individual neurons and finally to models of how behavior can arise from abstract neural modules that represent complete subsystems.
These include models of the longterm, and shortterm plasticity, of neural systems and their relations 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 numbervalued weights) has the full power of a universal Turing machine,[226]
The first is to use crossvalidation and similar techniques to check for the presence of overtraining and optimally select hyperparameters to minimize the generalization error.
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 componentbased neural 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 and by grouping examples in socalled minibatches.
For example, by introducing a recursive least squares algorithm for CMAC neural network, the training process only takes one step to converge.[92]
No neural network has solved computationally difficult problems such as the nQueens problem, the travelling salesman problem, or the problem of factoring large integers.
Back propagation is a critical part of most artificial neural networks, although no such mechanism exists in biological neural networks.[228]
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.[229]
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.
The motivation behind Artificial neural networks is not necessarily to strictly replicate neural function, but to use biological neural networks as an inspiration.
A central claim of artificial neural networks is therefore that it embodies some new and powerful general principle for processing information.
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 'somethingfornothing quality, one that imparts a peculiar aura of laziness and a distinct lack of curiosity about just how good these computing systems are.
argued that the brain selfwires 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 compel a neural network designer to fill many millions of database rows for its connections – 
Schmidhuber notes that the resurgence of neural networks in the twentyfirst 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 millionfold, making the standard backpropagation algorithm feasible for training networks that are several layers deeper than before.[234]
Neuromorphic engineering addresses the hardware difficulty directly, by constructing nonvonNeumann chips to directly implement neural networks in circuitry.
Arguments against Dewdney's position are that neural networks have been successfully used to solve many complex and diverse tasks, ranging from autonomously flying aircraft[237]
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.
Although it is true that analyzing what has been learned by an artificial neural network is difficult, it is much easier to do so than to analyze what has been learned by a biological neural network.
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.[240][241]
The simplest, static types have one or more static components, including number of units, number of layers, unit weights and topology.
 On 18. juni 2021
What is Artificial Intelligence Exactly?
Subscribe here: Check out the previous episode: Become a Patreo
Artificial Intelligence: Mankind's Last Invention
Artificial Intelligence: Mankind's Last Invention  Technological Singularity Explained Signup and get 20% off a premium subscription! ..
*MUST SEE* Dangers of artificial intelligence documentary (2018)
The future is looking pretty bleak... This video uses copyrighted material in a manner that does not require approval of the copyright holder. It is a fair use under ...
5 CREEPIEST Things Done By Artificial Intelligence Robots...
Previous Videos: Narrated By: Ty Notts Music: Co.Ag ___ FB: .
Scary Artificial Intelligence Breakthrough  What You're About to See will Shock You
Follow us on Facebook ▷    Youtube \ Video \ Hedgehog world news prophetic prophecy strange mystery ..
Elon Musk  Artificial Intelligence, Neuralink & New Forms of Government on Mars
Elon Musk discussed his concerns about artificial intelligence and his hope for forming a symbiosis with AI through his Neuralink company at SXSW on March ...
The A.I. Takeover Is Here! Should We Fear Artificial Intelligence?
John Lennox AI discussion starts at 22:30  This is the shortened version. On Oct. 9, 2018, John Lennox addressed the critical questions surrounding artificial ...
Artificial Intelligence
Intelligent machines are no longer science fiction and experts seem divided as to whether artificial intelligence should be feared or welcomed. In this video I ...
What is artificial intelligence? Top AI features of Honor view 10 [Hindiहिन्दी]
AI has becoming famous since smartphone companies have introduced these features in their devices. If you have been wondering what AI is, so in this video I ...
The Dangers of Artificial Intelligence  Robot Sophia makes fun of Elon Musk  A.I. 2018
The Dangers of Artificial Intelligence  Robot Sophia jokes and makes fun of Elon Musk  A.I. 2017  2ndEarth Alternative (22/04/2017) ** Help this channel grow ...