pasaba por aqui
  • Member for 3 years, 11 months
  • Last seen more than a week ago
  • Barcelona, Spain
Can LSTM neural networks be sped up by a GPU?
9 votes

From Nvidia www (https://developer.nvidia.com/discover/lstm): Accelerating Long Short-Term Memory using GPUs The parallel processing capabilities of GPUs can accelerate the LSTM training and ...

View answer
Why is the perceptron criterion function differentiable?
Accepted answer
7 votes

$\max(-y_i(w x_i), 0)$ is not partial derivable respect $w$ if $w x_i=0$. Loss functions are problematic when not derivable in some point, but even more when they are flat (constant) in some interval ...

View answer
Can the hidden layer prior to the ouput layer have less hidden units than the output layer?
Accepted answer
7 votes

A layer with bigger number of nodes than previous one is something very common. Some examples are: strategies encoder-decoder (autoencoders) where the encoder typically has layers with a decreasing ...

View answer
What kind of simulated environment is complex enough to develop a general AI?
5 votes

I think this is one of the best AGI related questions I've see in this forum. I will skip all thematic about "what is an AGI", "simulation game", ... These topics have been discussed during decades ...

View answer
How to refine K-means clustering on a data set?
Accepted answer
5 votes

The usual parameters to adjust in a k-means: Number of clusters (recall many clusters can have same label). Distance definition (euclidean is the most basic, Gauss is an improvement) Selection of ...

View answer
Why is Common Lisp, Python and Prolog used in artificial intelligence?
Accepted answer
3 votes

If we talk about applied AI, the choice of a programming language for an AI application has the same points to be taken into account that in any other software area: speed of generated code, ...

View answer
How to verify classification model trained on classification dataset on a detection dataset for classification purpose?
2 votes

To verify the accuracy of the classification stage, you will need labeled images with a single car. To train and verify accuracy of the detection stage and full system, you can: in the datasets with ...

View answer
What do we mean by "infrequent features"?
Accepted answer
2 votes

We will describe the input to the network as a vector, called features vector. Each component of this vector is usually related to some "real world" information, by example "age of the ...

View answer
How to tell a neural network that: "your i-th input is special"
2 votes

Assume the image can contain objects of class $C_1 \dots C_c$. Assume a set of additional inputs that has a meaning of questions as "contains the image a C_i or C_j or ... ?". The main ...

View answer
Should I use additional empty category in some categorical problems?
Accepted answer
2 votes

In short: yes, you must allow "do nothing" decision as a first level result. Your system must decide the action to be taken, including "do nothing" action. This is different to low ...

View answer
How to model inhibitory synapses in the artificial neuron?
2 votes

In biology, when the presynaptic releases a neurotransmitter (a positive amount of them, obviously), this neurotransmitter reaches the postsynaptic vesicles causing an excitatory (depolarization) or ...

View answer
Are my computations of the forward and backward pass of a neural network with one input, hidden and output neurons correct?
Accepted answer
2 votes

One important point I missed in first review: error is a summatory, its derivative is also a summatory. About offsets "b": usually they are different in each cell (if not fixed to some value, as 0). ...

View answer
Is there a naming convention for network weights for multilayer networks?
Accepted answer
2 votes

When the system grows matrix notation is used, as a=Wx, being a (input to activation function in hidden layer) and x (values from input layer) column vectors, transpose of (a1,a2,...a_m) and (x1,x2,......

View answer
Strong AI vs Singularity - which should happen first?
Accepted answer
2 votes

The definition of "technological singularity" answers the question: The technological singularity (also, simply, the singularity) is the hypothesis that the invention of artificial ...

View answer
How to mathematically/logically represent the sense of sentences like "The cat drinks milk"?
Accepted answer
2 votes

Let start by classify the phrases you propose: The cat drinks milk. => action Sun is yellow. => descriptive/declarative, immutable I was at work yesterday. => descriptive, time related 1) The ...

View answer
Does k consistency always imply (k - 1) consistency?
2 votes

Define P as a CSP where X, Y are the variables, domain of both is {1,2,3,4} and conditions in normal form are: node-condition X<4 arc-condition X=Y P is 2-consistent (arc consistent) because for ...

View answer
Are convolutional neural networks inspired by the human brain?
1 votes

In the eye, the retinal ganglion cells have a receptive field that is equivalent to some types of convolution filters, most of them edge detectors. The brain is a big unknown, nobody knows how it does ...

View answer
Which predictive algorithm can be used to predict a number given other numbers?
1 votes

Impossible to solve until you define an error measurement ( by example $|R-R'|$ or $(R-R')^2$ ) and how this error changes when A, B and C change. Extreme example: assume $R()$ is random (unrelated to ...

View answer
What exactly is the eigenspace of a graph (in spectral clustering)?
Accepted answer
1 votes

In spectral clustering we not find the eigenvectors of a graph (a graph is not a matrix) but the eigenvalues/eigenvectors of the Laplacian matrix related to the adjacency matrix of the graph: graph =&...

View answer
Does replacing 3x3 filters with 3x1 and 1x3 filters improve the performance?
1 votes

If the filter is separable, that is, the NxM kernel can be mathematically equal to the convolution of a Nx1 filter and a 1xM filter, there are a very important increase in performance. Using separable ...

View answer
How is the error calculated with multiple output neurons in the neural network?
1 votes

As you say, the outputs are modeled as a vector, each output in one vector component. In regression problems: The most common loss function, like in the scalar case, is the square error. Skipping ...

View answer
Transfer Learning of Numerical Data
Accepted answer
1 votes

It seems like transfer learning is only applicable to neural networks. Is this a correct assumption? No. Wiki page give you pointers of several examples in other methodologies. While I was looking ...

View answer
When should we use separable convolution?
Accepted answer
1 votes

Context of the question This is a link to the text cited in the question. It refers to the usage of SeparableConv2D (tf, keras name). A related question on StackOverflow is "What is the ...

View answer
What happens when an opponent a neural network is playing with does not obey the rules of the game (i.e. cheats)?
1 votes

"Will a neural network adapt to that ?" No. The big functional difference between human mind and neural networks : human mind learns by itself, a NN not. If we call NN the net with its ...

View answer
Is there an AI technology that can predict human behaviour?
1 votes

Is there an AI technology out there or being developed that can predict human behaviour ? If it can predict (all) human behavior, it can act as an human, thus, it will be the first real (strong) AI. ...

View answer
Are AI algorithms capable of self-repair?
1 votes

The question and the example are a few contradictory. The example is about a physical brain damage. Computer systems with the ability to self-repair exists from 1970's. They can repair a damaged disk ...

View answer
In number classification using neural network, is training with edge image better than gray image?
Accepted answer
1 votes

Theoretically you will have no gain in the error ratio if the system preprocess the images with a linear high-pass filter before to send the image to the NN. Let see a simple 1-dimension case that ...

View answer
What are examples of simple problems and applications that can be solved with AI techniques?
1 votes

I will assume you talk about applied AI (in generalized/strong AI we have nothing yet to program :-). You can look at any university course of introduction to AI and see its chapters and the program ...

View answer
Predict frequently purchased items under certain conditions with customer purchasing history data
1 votes

Let start by the concrete question, and follow talking about the general problem. a) The concrete question "find items that are particularly frequently purchased through online stores by paying ...

View answer
How is the word embedding represented in the paper "Recurrent neural network based language model"?
Accepted answer
1 votes

Input vector contains two concatenated parts. The low part represents the current word: word in time t encoded using 1-of-N coding [...] - size of vector x is equal to size of vocabulary V (this ...

View answer