Abstract: The present disclosure relates to a method and device for providing training content. A method may comprise displaying a question card including a first area and a second area; determining a recommended question using an artificial intelligence (AI) model trained on the basis of training data of a user; displaying, on the first area of a screen of a learner terminal, a plurality of prediction values for information obtained by analyzing a correlation between the training ability of the user and the recommended question using the AI model, together with the recommended question; displaying summary information about the recommended question on the second area of the screen of the learner terminal; and displaying a question object of the recommended question on the screen of the learner terminal when the user decides to solve the recommended question on the basis of the plurality of prediction values and the summary information.

Abstract: Disclosed herein are operation methods of a memory controller which controls a memory device. The method includes storing write data in a first area of the memory device, extracting first error position information indicating a position of at least one error included in data stored in the first area, storing the first error position information in a second area of the memory device, reading read data from the first area of the memory device, reading the first error position information from the second area of the memory device, refining the read data based on the first error position information to generate refined data, performing soft decision decoding based on the refined data to generate corrected data, and outputting the corrected data.

Abstract: In the present specification, a method of performing pre-training using an automated machine learning (AutoML) model by a server includes: using a first model for performing a first task to generate a second model for a second task; inputting, to the Auto ML model, a preset feature based on 1) components of the first model and the second model and 2) an element obtainable from training of the first model and generating of the second model as a state value; and changing the first model using the AutoML model.

Abstract: The present invention relates to a user knowledge tracking method with more improved accuracy. An operation method of a user drop-out rate prediction system including a plurality of encoder neural networks and a plurality of decoder neural networks may include the steps of: inputting question information to a kth encoder neural network and inputting response information to a kth decoder neural network; generating query data, which is information about a question of which the correct answer probability is desired to be identified by the user, by reflecting a weight to the response information, and generating attention information to be used as a weight for the query data by reflecting a weight to the question information; and learning the user drop-out rate prediction system using the attention information as a weight for the query data.

Abstract: An error correction circuit includes a memory that stores at least one decoding parameter, a low density parity check (LDPC) decoder that includes a first variable node storing one bit of the data, receives the at least one decoding parameter from the memory, decides a degree of the first variable node based on the at least one decoding parameter, and decides a decoding rule necessary for decoding of the one bit based on the degree of the first variable node, and an adaptive decoding controller that outputs corrected data based on a decoding result of the LDPC decoder.

Abstract: The present disclosure relates to a system capable of increasing the accuracy of a prediction result when predicting a user drop-out rate or predicting a correct answer probability of a user in an online learning environment, and further relates to an operation method of the system. A system according to the present disclosure may include a plurality of encoder neural networks and a plurality of decoders, and may input question information to a kth encoder neural network and input response information to kth decoder neural network to learn the system, thereby predicting the user drop-out rate information and the users correct answer probability information with higher accuracy on the basis of the learned system.

Abstract: A user knowledge tracking device is provided. The user knowledge tracking device use a transformer structure-based artificial intelligence model as a knowledge tracking model which is trained by inputting exercise information to an encoder thereof and inputting response information to a decoder thereof so as to predict a user's correct answer probability based on the trained knowledge tracking model.

Abstract: Provided is an operating method of a memory controller which comprises receiving first decision data of M bits from a memory device, where M is a natural number; converting the M-bit first decision data into second decision data of N bits, where N is a natural number less than M; and attempting a first decoding using the second decision data.

Abstract: A memory system includes; a memory device, a memory controller including a first interface, a second interface, and a first data processor having a first error correction code (ECC) engine, and a field programmable gate array (FPGA) including a third interface connected to the first interface, a fourth interface connected to the second interface, a fifth interface connected to an external host, and a second data processor having a second ECC engine. The memory controller may configure a normal write operation path or highly reliable write operation path.

Abstract: Disclosed is an extended service-providing system which provide an artificial intelligence prediction result associated with extended educational contents via an API access interface server, and the system may include an access interface server to communicate with an extended service server that provides the extended educational contents to a terminal of a user, and a learning content artificial intelligence server to communicate with the access interface server, and the access interface server determines whether the user has an access authority to use the learning content artificial intelligence server if an API transmitted from the terminal is received via the extended service server, and if the user is identified as having the access authority, the learning content artificial intelligence server transmits an artificial intelligence prediction result associated with the extended educational contents to the extended service server via the access interface server, in response to the API transmitted from the t

Abstract: An error correction circuit includes a memory that stores at least one decoding parameter, a low density parity check (LDPC) decoder that includes a first variable node storing one bit of the data, receives the at least one decoding parameter from the memory, decides a degree of the first variable node based on the at least one decoding parameter, and decides a decoding rule necessary for decoding of the one bit based on the degree of the first variable node, and an adaptive decoding controller that outputs corrected data based on a decoding result of the LDPC decoder.

Abstract: A storage device includes a nonvolatile memory device that includes a plurality of pages, each of which includes a plurality of memory cells, and a controller that receives first write data expressed by 2m states (m being an integer greater than 1) from an external host device. The controller in a first operating mode shapes the first write data to second write data, which are expressed by “k” states (k being an integer greater than 2) smaller in number than the 2m states, performs first error correction encoding on the second write data to generate third write data expressed by the “k” states, and transmits the third write data to the nonvolatile memory device for writing at a selected page from the plurality of pages.

Abstract: An operating method of a memory controller is provided. The operating method includes receiving a first read data and a second conversion information, the second conversion information including data obtained by converting a second read data based on a linear operation, and the first read data and the second read data including data read from same memory cells; converting the first read data based on the linear operation to generate a first conversion information; performing a logical operation on the first conversion information and the second conversion information to generate an operation information; performing an inverse operation of the linear operation on the operation information to generate a reliability information; and correcting an error of the first read data based on the first read data and the reliability information.

Abstract: An operating method of a storage controller which includes a high level decoder and a low level decoder includes generating first data that is a result of decoding initial data read from a nonvolatile memory device, and a first syndrome weight indicating an error level of the first data. The first data is output to a host when the first syndrome weight is a specific value. The high level decoder having a first error correction capability is selected to decode the first data, when the first syndrome weight exceeds a reference value, and the low level decoder having a second error correction capability lower than the first error correction capability is selected to decode the first data, when the first syndrome weight is the reference value or less.

Abstract: An error correction circuit includes a memory that stores at least one decoding parameter, a low density parity check (LDPC) decoder that includes a first variable node storing one bit of the data, receives the at least one decoding parameter from the memory, decides a degree of the first variable node based on the at least one decoding parameter, and decides a decoding rule necessary for decoding of the one bit based on the degree of the first variable node, and an adaptive decoding controller that outputs corrected data based on a decoding result of the LDPC decoder.

Abstract: A memory system includes; a memory device, a memory controller including a first interface, a second interface, and a first data processor having a first error correction code (ECC) engine, and a field programmable gate array (FPGA) including a third interface connected to the first interface, a fourth interface connected to the second interface, a fifth interface connected to an external host, and a second data processor having a second ECC engine. The memory controller may configure a normal write operation path or highly reliable write operation path.

Abstract: Provided is an LGVF path-following controller including: an LGVF control unit that is provided with a heading angle command for a wing-fixed unmanned aerial vehicle and guidance commands from the outside, and is provided with a computed estimation disturbance speed from a nonlinear disturbance control unit; a heading angle computation control unit that computes a final heading angle of the wing-fixed unmanned aerial vehicle using a difference between the heading angle of the wing-fixed unmanned aerial vehicle, which is computed by the LGVF control unit, and a heading angle of the wing-fixed unmanned aerial vehicle in an ideal environment where a disturbance is not present; and a nonlinear disturbance control unit that computes the estimation disturbance speed using the final heading angle provided from the heading angle computation control unit and pieces of sensor data on the wing-fixed unmanned aerial vehicle, which are provided from a sensor.

Abstract: A method of operating a decoder, which has variable nodes and check nodes, includes receiving variable-to-check (V2C) messages from the variable nodes using a first check node among the check nodes. The number of messages having a specific magnitude among the V2C messages is counted. The magnitude of a check-to-variable (C2V) message to be transmitted to a first variable node, among the variable nodes, is determined based on the count value and the magnitude of a V2C message of the first variable node.

Abstract: A decoder including a main memory, a flag memory and a decoding logic is provided. The flag memory is configured to store flag data and the decoding logic configured to perform an iteration. Further, the decoding logic is configured to: perform an ith operation using first data, wherein i is a natural number, flag-encode second data that is results obtained by performing the ith operation on the first data, store results obtained by performing the flag encoding on the second data in the flag memory as first flag data if the flag encoding succeeds, and store predetermined second flag data that is different from the first flag data of the second data in the flag memory if the flag encoding fails.

Abstract: An operating method of a memory controller that individually controls a plurality of memory units includes reading respective segments from the plurality of memory units based on a plurality of control signals; generating an output codeword based on the segments; performing error correction decoding on the output codeword; when a result of the error correction decoding indicates success, updating at least one of a plurality of accumulated error pattern information respectively corresponding to the plurality of memory units based on the result of the error correction decoding; and when the result of the error correction decoding indicates failure, regulating at least one of the plurality of control signals based on at least one of the plurality of accumulated error pattern information.