# Tag Info

4

In terms of transfer learning, semantic gap means different meanings and purposes behind the same syntax between two or more domains. For example, suppose that we have a deep learning application to detect and label a sequence of actions/words $a_1, a_2, \ldots, a_n$ in a video/text as a "greeting" in a society A. However, this knowledge in Society ...

3

The Flatten layer is used for collapsing an ND tensor into a 1D tensor. In your case, the inputs appear to be $28\times28$ images, so Flatten will convert that into a tensor with shape $1\times768$. Note that no information is lost. Flatten layers are usually used where you have a convolutional layer with dimensions $N\times M \times C$ (where $N$,$M$ are ...

2

Thanks for asking the question. I'm the author of the paper. The key point is that the weights $w$ cannot be updated directly with the new data as $w$ is not directly related with the output $y$ (see equation (1)). First, it is necessary to update $a$ first, which actually is directly related with $y$ via the activation function, i.e., $y = f(a)$ with $f(.)$ ...

2

Since $A_t$ is already determined (because we are calculating $Q(S_t,A_t)$), I think $\pi(A_t|S_t)$ is definitely 1. But what about $\mu (A_t|S_t)$? Is it 1 or not? You could assign values of 1 to each to get the right answer, but the situation is different. You can see that more clearly in the definition of action value, $q(s,a)$: q_{\pi}(s,a) = \mathbb{...

2

I would start by reviewing any available tools in NLP that can help you. I know two: Watson Personality Insights and Symanto thar provide API to develop this kind of solutions. The first one was one available in the past (Watson personality Insights) but unfortunately has been discontinued. The IBM Watson Personality Insights service enables applications to ...

2

Accuracy can sometimes be a very coarse metric. When it is applied to three class problems, people often take the class label with maximum predicted probability and predict that. The probabilities of the individual labels are ignored. I'd recommend that as well as accuracy you calculate sensitivity and specificity for each class and the area under the ROC ...

1

Would OpenCog fit the bill? I have had tremendous amounts of trouble building up the demos, which include some non-AGI stuff, but if I’ve read the manual correctly, I think there’s something here — https://opencog.org/

1

Not to my knowledge. The problem is that this is such an enormous task, it cannot really be tackled at once. So the obvious solution is to reduce the scope. In early AI people were using toy domains, whereas nowadays AI systems work more generally (but still perform better if the domain is restricted). So while (slow) progress is being made putting the ...

1

For the ANN, it should be the average of the error per instance from testing (prediction) when each instance is left out of training. ANNs can unfortunately learn based on the order of instances used for training, so it helps to train/test and then shuffle (permute, or randomly re-order) and then assign to k-folds, then train/test again in order to prevent ...

1

The wiki has a concise quote by Andreas Hein, where the gap is defined by "the difference in meaning between constructs formed within different representation systems". This connotes the core problem of translating meaning between an informal language (typically natural language) and a formal language (programing language or other formal symbolic ...

1

One can use simpler approach with deepC compiler and convert exported onnx model to c++. Check out simple example at deepC compiler sample test Compile onnx model for your target machine Checkout mnist.ir Step 1: Generate intermediate code % onnx2cpp mnist.onnx Step 2: Optimize and compile % g++ -O3 mnist.cpp -I ../../../include/ -isystem ../../../packages/...

1

The required shape of the tensor $T$ depends on the shape of other tensors that are involved in the same operations of that same tensor $T$ and the required/desired shape of the resulting tensor, in the same way that the number of columns of the matrix $M \in \mathbb{R}^{n \times m}$ needs to match the number of rows of the matrix $M' \in \mathbb{R}^{n' \... 1 I commonly use softmax for all 2-class or k-class problems, basically, because I always like to have an output node for each class. For sigmoid, i.e., logistic, you cannot estimate MSE for each sample using the relationship$E_i = \sum_c^C (y_c - \hat{y}_c)^2$, where$C$is the number of classes,$y_c$is 0 or 1 for true class membership, and$\hat{y}_c\$ is ...

1

Sigmoid is used for binary cases and softmax is its generalized version for multiple classes. But, essentially what they do is over exaggerate the distances between the various values. If you have values on a unit sphere, apply sigmoid or softmax on those values would lead to the points going to the poles of the sphere.

1

This seems to be a known problem, and intuitively seems reasonable. You might be interested in the paper Adversarial Training Can Hurt Generalization. The authors suggest that this might be because training on the perturbed data requires the model to learn more robust features, which means more samples are required to obtain performance comparable to a model ...

1

It looks like your network is overfitting, because the training loss carries on decreasing to zero even though validation loss levels off, and then starts to increase again. I would guess that your network is essentially "memorising" the training examples because you're getting a near zero loss in training. You could try: applying some form of ...

Only top voted, non community-wiki answers of a minimum length are eligible