Abstract: Verified snapshots are generated by obtaining, from one of a plurality of first nodes, a difference between a common data at a first time point and the common data at a second time point that is different from the first time point, generating a first snapshot of the common data at the first time point based on the difference, obtaining a hash of the common data at the first time point from one of the plurality of first nodes, and verifying the first snapshot at the first time point with the hash of the common data at the first time point.

Abstract: A computer-implemented method for reducing computation cost associated with a machine learning task performed by a computer system by implementing continuous control of attention for a deep learning network includes initializing a control-value function, an observation-value function and a sequence of states associated with a current episode. If a current epoch associated with the current episode is odd, an observation-action is selected, the observation-action is executed to observe a partial image, and the observation-value function is updated based on the partial image and the control-value function. If the current epoch is even, a control-action is selected, the control-action is executed to obtain a reward corresponding to the control-action, and the control-value function is updated based on the reward and the observation-value function.

Abstract: Rating models may be generated by obtaining a plurality of consumption values, obtaining a plurality of rating values, training a model that estimates consumption values and rating values by utilizing a plurality of consumer attributes for each consumer, a plurality of item attributes for each item, and a plurality of weights for each attribute of each combination of a consumer and an item. Each estimated consumption value is a function of the plurality of weights for each attribute of each combination of each consumer and each item that corresponds with the estimated consumption value, and each estimated rating value is a function of the plurality of consumer attributes of a consumer that corresponds with the estimated rating value, the plurality of item attributes of an item that corresponds with the estimated rating value, and the plurality of weights that corresponds with the estimated rating value.

Abstract: Verified snapshots are generated by obtaining, from one of a plurality of first nodes, a difference between a common data at a first time point and the common data at a second time point that is different from the first time point, generating a first snapshot of the common data at the first time point based on the difference, obtaining a hash of the common data at the first time point from one of the plurality of first nodes, and verifying the first snapshot at the first time point with the hash of the common data at the first time point.

Abstract: Verified snapshots are generated by obtaining, from one of a plurality of first nodes, a difference between a common data at a first time point and the common data at a second time point that is different from the first time point, generating a first snapshot of the common data at the first time point based on the difference, obtaining a hash of the common data at the first time point from one of the plurality of first nodes, and verifying the first snapshot at the first time point with the hash of the common data at the first time point.

Abstract: Verified snapshots are generated by obtaining, from one of a plurality of first nodes, a difference between a common data at a first time point and the common data at a second time point that is different from the first time point, generating a first snapshot of the common data at the first time point based on the difference, obtaining a hash of the common data at the first time point from one of the plurality of first nodes, and verifying the first snapshot at the first time point with the hash of the common data at the first time point.

Abstract: A method is provided for reducing a computational cost of deep reinforcement learning using an input image to provide a filtered output image composed of pixels. The method includes generating a moving gate in which the pixels of the filtered output image to be masked are assigned a first gate value and the pixels of the filtered output image to be passed through are assigned a second gate value. The method further includes applying the input image and the moving gate to a GCNN to provide the filtered output image such that only the pixels of the input image used to compute the pixels assigned the second gate value are processed by the GCNN while bypassing the pixels of the input image useable to compute the pixels assigned the first gate to reduce an overall processing time of the input image in order to provide the filtered output image.

Abstract: A method comprising calculating output values of a plurality of linear nodes connected to a maxout node in a neural network, calculating a temporary maximum value among the output values during the calculation of the output values, and terminating the calculation of a final output value of a first linear node of the plurality of linear nodes in response to a condition that a difference between the temporary maximum value and a temporary output value of the first linear node exceeds a threshold value during the calculation of the output values.

Abstract: A computer-implemented method for reducing computation cost associated with a machine learning task performed by a computer system by implementing continuous control of attention for a deep learning network includes initializing a control-value function, an observation-value function and a sequence of states associated with a current episode. If a current epoch associated with the current episode is odd, an observation-action is selected, the observation-action is executed to observe a partial image, and the observation-value function is updated based on the partial image and the control-value function. If the current epoch is even, a control-action is selected, the control-action is executed to obtain a reward corresponding to the control-action, and the control-value function is updated based on the reward and the observation-value function.

Abstract: A method is provided for reducing a computational cost of deep reinforcement learning using an input image to provide a filtered output image composed of pixels. The method includes generating a moving gate in which the pixels of the filtered output image to be masked are assigned a first gate value and the pixels of the filtered output image to be passed through are assigned a second gate value. The method further includes applying the input image and the moving gate to a GCNN to provide the filtered output image such that only the pixels of the input image used to compute the pixels assigned the second gate value are processed by the GCNN while bypassing the pixels of the input image useable to compute the pixels assigned the first gate to reduce an overall processing time of the input image in order to provide the filtered output image.

Abstract: Verified snapshots are generated by obtaining, from one of a plurality of first nodes, a difference between a common data at a first time point and the common data at a second time point that is different from the first time point, generating a first snapshot of the common data at the first time point based on the difference, obtaining a hash of the common data at the first time point from one of the plurality of first nodes, and verifying the first snapshot at the first time point with the hash of the common data at the first time point.

Abstract: Verified snapshots are generated by obtaining, from one of a plurality of first nodes, a difference between a common data at a first time point and the common data at a second time point that is different from the first time point, generating a first snapshot of the common data at the first time point based on the difference, obtaining a hash of the common data at the first time point from one of the plurality of first nodes, and verifying the first snapshot at the first time point with the hash of the common data at the first time point.

Abstract: A computer implemented method is provided for generating a prediction of a next musical note by a computer having at least a processor and a memory. A computer processor system is also provided for generating a prediction of a next musical note. The method includes storing sequential musical notes in the memory. The method further includes dividing, by the processor, the sequential musical notes into sections of a given length based on a Generative Theory of Tonal Music. The method also includes generating, by the processor, the prediction of the next musical note based upon a music model, the sections, and the sequential musical notes stored in the memory. The given length is determined based on one or more conditions.

Abstract: Rating models may be generated by obtaining a plurality of consumption values, obtaining a plurality of rating values, training a model that estimates consumption values and rating values by utilizing a plurality of consumer attributes for each consumer, a plurality of item attributes for each item, and a plurality of weights for each attribute of each combination of a consumer and an item. Each estimated consumption value is a function of the plurality of weights for each attribute of each combination of each consumer and each item that corresponds with the estimated consumption value, and each estimated rating value is a function of the plurality of consumer attributes of a consumer that corresponds with the estimated rating value, the plurality of item attributes of an item that corresponds with the estimated rating value, and the plurality of weights that corresponds with the estimated rating value.

Abstract: A method comprising calculating output values of a plurality of linear nodes connected to a maxout node in a neural network, calculating a temporary maximum value among the output values during the calculation of the output values, and terminating the calculation of a final output value of a first linear node of the plurality of linear nodes in response to a condition that a difference between the temporary maximum value and a temporary output value of the first linear node exceeds a threshold value during the calculation of the output values.

Abstract: A computer implemented method is provided for generating a prediction of a next musical note by a computer having at least a processor and a memory. A computer processor system is also provided for generating a prediction of a next musical note. The method includes storing sequential musical notes in the memory. The method further includes generating, by the processor, the prediction of the next musical note based upon a music model and the sequential musical notes stored in the memory. The method also includes updating, by the processor, the music model based upon the prediction of the next musical note and an actual one of the next musical note. The method additionally includes resetting, by the processor, the memory at fixed time intervals.

Abstract: In a transmitter (2001), when generating a transmission frame having no limitation to a window size, a batch-transmission-end flag generating circuit (2004) and a sequence number generating circuit (2005) respectively adds a batch-transmission-end flag and a sequence number to the transmission frame. In a receiver, if an omission of a sequence number is detected as a result of analyzing sequence numbers of frames having received from the transmitter (2001), retransmission request is made when receiving a frame whose batch-transmission-end flag indicates the end. In this way, retransmission is possible in data transmission using UI frames, and the communication efficiency can be improved.

Abstract: The present invention is a network layer protocol used for free-space optical transmission utilizing an LED or LD as a light source. In order to connect to a device, the network layer issues a connection request command (LAP_con_req2) to a lower layer when the network layer has received a connection request command (LM_con_req1) from an upper layer. Furthermore, when the network layer has received a connection confirmation command reception notification (LAP_con_conf1) from the lower layer, the network layer issues a connection confirmation command reception notification (LM_con_conf2) to the upper layer without issuing a data transfer request command to the lower layer. Accordingly, the invention provides a network layer protocol with which time for a connection or disconnection is reduced.

Abstract: Provided is a communication system including a transmitter and a receiver which carry out communication by establishing connection of their plurality of communication layers. The transmitter generates a connection request containing a command and data required for connecting a number of contiguously adjacent layers among the plurality of communication layers and transmits the connection request to the receiver. The receiver receives a connection request containing a command and data required for connecting a number of contiguously adjacent layers among the plurality of communication layers, extracts the command and data from the connection request, and establishes connection for the plurality of communication layers based on the command and data. In this way, the time taken to establish connection is reduced. Therefore, even when the connection is cut off during the data exchange, the connection can be established again without taking much time, allowing quick recovery of data exchange.

Abstract: The demodulation circuit of the present invention is a demodulation circuit, connected with a plurality of light-receiving sections each for receiving an optical signal and converting the signal into a binary pulse signal, operable to select and demodulate a pulse signal out of pulse signals that are supplied from the light-receiving sections, respectively, the demodulation circuit including: a judgment and selection section for detecting timing with which High level and Low level of each of the pulse signals are switched and for selecting at least one pulse signal based on the timing; and a demodulation section for demodulating the pulse signal selected by the judgment and selection section. Consequently, the demodulation circuit easily selects and demodulates a signal whose jitter component is small out of a plurality of supplied signals.