Abstract: A method for training a computerized mechanical device, comprising: receiving data documenting actions of an actuator performing a task in a plurality of iterations; calculating using the data a neural network dataset and used for performing the task; gathering in a plurality of reward iterations a plurality of scores given by an instructor to a plurality of states, each comprising at least one sensor value, while a robotic actuator performs the task according to the neural network; calculating using the plurality of scores a reward dataset used for computing a reward function; updating at least some of the neural network's plurality of parameters by receiving in each of a plurality of policy iterations a reward value computed by applying the reward function to another state comprising at least one sensor value, while the robotic actuator performs the task according to the neural network; and outputting the updated neural network.

Abstract: A system and method of automated optimization of a Neural Network (NN) model by at least one processor may include: receiving a pretrained NN model; constructing at least one master NN model, based on the pretrained NN model, each master NN model comprising a plurality of subnetworks; for each master NN model, constructing a router NN, adapted to direct one or more data instances of an input dataset to specific subnetworks of the master NN model; for each master NN model, calculating a utility score; and selecting a master NN model of the at least one constructed master NN models, based on the utility score.

Abstract: Training neural networks by constructing a neural network model having neurons each associated with a quantized activation function adapted to output a quantized activation value. The neurons are arranged in layers and connected by connections associated quantized connection weight functions adapted to output quantized connection weight values. During a training process a plurality of weight gradients are calculated during backpropagation sub-processes by computing neuron gradients, each of an output of a respective the quantized activation function in one layer with respect to an input of the respective quantized activation function. Each neuron gradient is calculated such that when an absolute value of the input is smaller than a positive constant threshold value, the respective neuron gradient is set as a positive constant output value and when the absolute value of the input is smaller than the positive constant threshold value the neuron gradient is set to zero.

Abstract: A method for training a computerized mechanical device, comprising: receiving data documenting actions of an actuator performing a task in a plurality of iterations; calculating using the data a neural network dataset and used for performing the task; gathering in a plurality of reward iterations a plurality of scores given by an instructor to a plurality of states, each comprising at least one sensor value, while a robotic actuator performs the task according to the neural network; calculating using the plurality of scores a reward dataset used for computing a reward function; updating at least some of the neural network's plurality of parameters by receiving in each of a plurality of policy iterations a reward value computed by applying the reward function to another state comprising at least one sensor value, while the robotic actuator performs the task according to the neural network; and outputting the updated neural network.

Abstract: Training neural networks by constructing a neural network model having neurons each associated with a quantized activation function adapted to output a quantized activation value. The neurons are arranged in layers and connected by connections associated quantized connection weight functions adapted to output quantized connection weight values. During a training process a plurality of weight gradients are calculated during backpropagation sub-processes by computing neuron gradients, each of an output of a respective the quantized activation function in one layer with respect to an input of the respective quantized activation function. Each neuron gradient is calculated such that when an absolute value of the input is smaller than a positive constant threshold value, the respective neuron gradient is set as a positive constant output value and when the absolute value of the input is smaller than the positive constant threshold value the neuron gradient is set to zero.

Abstract: A method and computing program for providing a user computing platform with a response to a query, the response comprising indications to one or more Universal Resource Identifier optionally with instructions on how to get the relevant information from there, and how to format the response. Thus a user computing platform receives information directly from a content provider, whose rights are not infringed by the query engine. If payment or other limitations are imposed by the content provider or by the user, they are handled between the user and the content provider, without intervention by the query engine.

Abstract: A method and computing program for providing a user computing platform with a response to a query, the response comprising indications to one or more Universal Resource Identifier optionally with instructions on how to get the relevant information from there, and how to format the response. Thus a user computing platform receives information directly from a content provider, whose rights are not infringed by the query engine. If payment or other limitations are imposed by the content provider or by the user, they are handled between the user and the content provider, without intervention by the query engine.

Abstract: A method and computing program for providing a user computing platform with a response to a query, the response comprising indications to one or more Universal Resource Identifier optionally with instructions on how to get the relevant information from there, and how to format the response. Thus a user computing platform receives information directly from a content provider, whose rights are not infringed by the query engine. If payment or other limitations are imposed by the content provider or by the user, they are handled between the user and the content provider, without intervention by the query engine.

Abstract: A method of evaluating a semantic relatedness of terms. The method comprises providing a plurality of text segments, calculating, using a processor, a plurality of weights each for another of the plurality of text segments, calculating a prevalence of a co-appearance of each of a plurality of pairs of terms in the plurality of text segments, and evaluating a semantic relatedness between members of each the pair according to a combination of a respective the prevalence and a weight of each of the plurality of text segments wherein a co-appearance of the pair occurs.

Abstract: A method of evaluating a semantic relatedness of terms. The method comprises providing a plurality of text segments, calculating, using a processor, a plurality of weights each for another of the plurality of text segments, calculating a prevalence of a co-appearance of each of a plurality of pairs of terms in the plurality of text segments, and evaluating a semantic relatedness between members of each the pair according to a combination of a respective the prevalence and a weight of each of the plurality of text segments wherein a co-appearance of the pair occurs.

Abstract: A method of evaluating a semantic relatedness of terms. The method comprises providing a plurality of text segments, calculating, using a processor, a plurality of weights each for another of the plurality of text segments, calculating a prevalence of a co-appearance of each of a plurality of pairs of terms in the plurality of text segments, and evaluating a semantic relatedness between members of each the pair according to a combination of a respective the prevalence and a weight of each of the plurality of text segments wherein a co-appearance of the pair occurs.