Integrated neural network and semantic system
An integrated neural network and semantic system applies a neural network to interpret an image, determines a syntactical element corresponding to the image in accordance with the interpretation, and determines a first probability that represents a confidence level that the correspondence is accurate. A semantic chain and associated second probability are then generated based on the syntactical element and the first probability, whereby the second probability represents the system's confidence level that the semantic chain accurately reflects objective reality. A natural language communication is generated for delivery to a user that comprises syntactical elements that are in accordance with the semantic chain and the second probability. The communication may further be expected to result in receiving information that will influence the confidence level that the semantic chain accurately reflects objective reality.
1. A computer-implemented method comprising:
applying automatically a computer-implemented trained neural network to interpret one image, wherein the one image comprises a first plurality of pixels, wherein the computer-implemented trained neural network is trained on a training set comprising images associated with syntactical elements to infer syntactical elements corresponding to pixel patterns within images;
determining automatically in accordance with the interpretation by the computer-implemented trained neural network of the one image a first syntactical element that corresponds to a first subset of the first plurality of pixels;
determining automatically a first probability by the computer-implemented trained neural network that represents a confidence level of the accuracy of the correspondence of the first syntactical element to the first subset of the first plurality of pixels;
generating automatically a first semantic chain that is based, at least in part, upon the first syntactical element;
determining automatically a second probability that is based, at least in part, on the first probability, wherein the second probability represents a confidence level that the first semantic chain reflects objective reality, wherein the second probability is based on a plurality of probabilities that each represent a confidence level of accuracy of a correspondence between a syntactical element and a subset of the first plurality of pixels, wherein each of the correspondences and associated probabilities is in accordance with an interpretation of each of the subsets of the first plurality of pixels by the computer-implemented trained neural network; and
generating automatically a natural language-based communication for delivery to a user, wherein the communication comprises syntactical elements that are in accordance with the first semantic chain and the second probability.
2. The method of claim 1 , further comprising:
applying automatically the computer-implemented neural network, wherein the computer-implemented trained neural network is a convolutional neural network.
3. The method of claim 1 , further comprising:
determining automatically the first probability, wherein the first probability is determined in accordance with information that is accessed from one or more feature detection nodes of the computer-implemented trained neural network.
4. The method of claim 1 , further comprising:
generating automatically the first semantic chain, wherein the first semantic chain is further based upon a linking of a plurality of semantic chains.
5. The method of claim 1 , further comprising:
generating automatically the natural language-based communication comprising the syntactical elements, wherein the syntactical elements are further in accordance with a linking of the first semantic chain with a second semantic chain.
6. The method of claim 1 , further comprising:
generating automatically the natural language-based communication, wherein the communication is expected to result in receiving information that will influence the confidence level that the first semantic chain reflects objective reality.
7. A computer-implemented system comprising one or more processor-based devices configured to:
apply automatically a computer-implemented trained neural network to interpret one image, wherein the one image comprises a first plurality of pixels, wherein the computer-implemented trained neural network is trained on a training set comprising images associated with syntactical elements to infer syntactical elements corresponding to pixel patterns within images;
determine automatically in accordance with the interpretation by the computer-implemented trained neural network of the one image a first syntactical element that corresponds to a first subset of the first plurality of pixels;
determine automatically a first probability by the computer-implemented trained neural network that represents a confidence level of the accuracy of the correspondence of the first syntactical element to the first subset of the first plurality of pixels;
generate automatically a first semantic chain that is based, at least in part, upon the first syntactical element;
determine automatically a second probability that is based, at least in part, on the first probability, wherein the second probability represents a confidence level that the first semantic chain reflects objective reality, wherein the second probability is based on a plurality of probabilities that each represent a confidence level of accuracy of a correspondence between a syntactical element and a subset of the first plurality of pixels, wherein each of the correspondences and associated probabilities is in accordance with an interpretation of each of the subsets of the first plurality of pixels by the computer-implemented trained neural network; and
generate automatically a natural language-based communication for delivery to a user, wherein the communication comprises syntactical elements that are in accordance with the first semantic chain and the second probability.
8. The system of claim 7 , further comprising the one or more processor-based devices configured to:
apply automatically the computer-implemented neural network, wherein the computer-implemented trained neural network is a convolutional neural network.
9. The system of claim 7 , further comprising the one or more processor-based devices configured to:
determine automatically the first probability, wherein the first probability is determined in accordance with information that is accessed from one or more feature detection nodes of the computer-implemented trained neural network.
10. The system of claim 7 , further comprising the one or more processor-based devices configured to:
generate automatically the first semantic chain, wherein the first semantic chain is further based upon a linking of a plurality of semantic chains.
11. The system of claim 7 , further comprising the one or more processor-based devices configured to:
generate automatically the natural language-based communication comprising the syntactical elements, wherein the syntactical elements are further in accordance with a linking of the first semantic chain with a second semantic chain.
12. The system of claim 7 , further comprising the one or more processor-based devices configured to:
generate automatically the natural language-based communication, wherein the communication is expected to result in receiving information that will influence the confidence level that the first semantic chain reflects objective reality.
13. The system of claim 12 , further comprising the one or more processor-based devices configured to:
generate automatically the natural language-based communication, wherein the communication comprises an interrogative directed to the user.
14. An apparatus comprising:
one or more cameras;
one or more processors configured to:
receive a first set of information from the one or more cameras, wherein the first set of information comprises a first plurality of pixels within an image;
apply automatically a computer-implemented trained neural network to interpret the first plurality of pixels, wherein the computer-implemented trained neural network is trained on a training set comprising images associated with syntactical elements to infer syntactical elements corresponding to pixel patterns within images;
determine automatically in accordance with the interpretation of the first plurality of pixels by the computer-implemented trained neural network a first syntactical element that corresponds to a first subset of the first plurality of pixels;
determine automatically a first probability by the computer-implemented trained neural network that represents a confidence level of the accuracy of the correspondence of the first syntactical element to the first subset of the first plurality of pixels;
provide the first syntactical element and the first probability to a computer-implemented function that generates automatically a first semantic chain that is based, at least in part, upon the first syntactical element and determines automatically a second probability that is based, at least in part, on the first probability, wherein the second probability represents a confidence level that the first semantic chain reflects objective reality, wherein the second probability is based on a plurality of probabilities that each represent a confidence level of accuracy of a correspondence between a syntactical element and a subset of the first plurality of pixels, wherein each of the correspondences and associated probabilities is in accordance with an interpretation of each of the subsets of the first plurality of pixels by the computer-implemented trained neural network; and
deliver automatically a natural language-based communication to a user, wherein the communication is automatically generated and comprises syntactical elements that are in accordance with the first semantic chain and the second probability.
15. The apparatus of claim 14 , further comprising the one or more processors configured to:
determine automatically the first probability, wherein the first probability is determined in accordance with information that is accessed from one or more feature detection nodes of the computer-implemented trained neural network.
16. The apparatus of claim 14 , further comprising the one or more processors configured to:
generate automatically the natural language-based communication comprising the syntactical elements, wherein the syntactical elements are further in accordance with a linking of the first semantic chain with a second semantic chain.
17. The apparatus of claim 14 , further comprising the one or more processors configured to:
generate automatically the natural language-based communication, wherein the communication is expected to result in receiving information that will influence the confidence level that the first semantic chain reflects objective reality.