-
公开(公告)号:US12124814B2
公开(公告)日:2024-10-22
申请号:US17720912
申请日:2022-04-14
申请人: NAVER CORPORATION
发明人: Julien Perez , Denys Proux , Michael Niemaz
IPC分类号: G06F16/9032 , G06F16/332 , G06F40/30 , G06F40/58 , G06N3/042 , G06N3/0455 , G06N3/0464 , G06N3/0895 , G06N3/10
CPC分类号: G06F40/58 , G06F16/90332 , G06N3/10
摘要: A confidence estimation system includes: a neural network including at least one an attention module including N heads configured to: generate attention matrices based on interactions between tokens for words in an input sequence of words, the input sequence of words including a word that is obscured; and determine the word that is obscured in the input sequence; and a confidence module configured to determine a confidence value indicative of a probability of the neural network correctly determining the word that is obscured, the confidence module determining the confidence value of the word that is obscured using a convolutional neural network that projects the attention matrices generated by the attention module over a multi-dimensional space, the attention matrices recording interactions between the tokens in the input sequence of words without information regarding the tokens for the words and the word that is obscured.
-
公开(公告)号:US12119840B2
公开(公告)日:2024-10-15
申请号:US18362137
申请日:2023-07-31
发明人: Ariel Doubchak , Dikla Shapiro , Evgeny Blaichman , Lital Cohen , Amit Berman
CPC分类号: H03M13/1108 , G06N3/10 , H03M13/1111
摘要: A machine-learning (ML) error-correcting code (ECC) controller may include a hard-decision (HD) ECC decoder optimized for high-speed data throughput, a soft-decision (SD) ECC decoder optimized for high-correctability data throughput, and a machine-learning equalizer (MLE) configured to variably select one of the HD ECC decoder or the SD ECC decoder for data throughput. An embodiment of the ML ECC controller may provide speed-optimized HD throughput based on a linear ECC. The linear ECC may be a soft Hamming permutation code (SHPC).
-
公开(公告)号:US20240330417A1
公开(公告)日:2024-10-03
申请号:US18738379
申请日:2024-06-10
申请人: Ciena Corporation
摘要: Systems and methods for embedding concealed meta-data into DNNs. Specifically, the system and method presented consists of receiving a trained neural network that includes one or more layers each having weights. The disclosed process includes transforming at least one layer to a transformed domain, adding information to the layer(s) in the transformed domain, and performing an inverse domain transform on at least one layer such that the layer(s) has new weights with an embedded watermark.
-
公开(公告)号:US12105625B2
公开(公告)日:2024-10-01
申请号:US17588240
申请日:2022-01-29
申请人: Ceremorphic, Inc.
发明人: Lizy Kurian John , Venkat Mattela , Heonchul Park
IPC分类号: G06F12/04 , G06N3/0464 , G06N3/10
CPC分类号: G06F12/04 , G06N3/0464 , G06N3/10 , G06F2212/16
摘要: A programmable address generator has an iteration variable generator for generation of an ordered set of iteration variables, which are re-ordered by an iteration variable selection fabric, which delivers the re-ordered iteration variables to one or more address generators. A configurator receives an instruction containing fields which provide configuration constants to the address generator, iteration variable selection fabric, and address generators. After configuration, the address generators provide addresses coupled to a memory. In one example of the invention, the address generators generate an input address, a coefficient address, and an output address for performing convolutional neural network inferences.
-
公开(公告)号:US12086657B2
公开(公告)日:2024-09-10
申请号:US18305683
申请日:2023-04-24
申请人: Intel Corporation
摘要: Systems, apparatuses and methods may provide for technology that detects a tensor operation in an application, wherein the tensor operation has an unspecified tensor input size, determines the input tensor size at runtime, and selects a partition configuration for the tensor operation based at least in part on the input tensor size and one or more runtime conditions. In one example, the technology searches a lookup table for the input tensor size and at least one of the runtime condition(s) to select the partition configuration.
-
公开(公告)号:US20240296346A1
公开(公告)日:2024-09-05
申请号:US18383858
申请日:2023-10-25
申请人: Apple Inc.
摘要: The subject technology receives code corresponding to a neural network (NN) model and a set of weights for the NN model. The subject technology determines a set of layers that are mutable in the NN model. The subject technology determines information for mapping a second set of weights to the set of weights for the NN model. The subject technology generates metadata corresponding to the set of layers that are mutable, and the information for mapping the second set of weights to the set of weights for the NN model, wherein the generated metadata enables updating the set of layers that are mutable during execution of the NN model.
-
公开(公告)号:US12079723B2
公开(公告)日:2024-09-03
申请号:US18183515
申请日:2023-03-14
申请人: Tesla, Inc.
CPC分类号: G06N3/08 , G05B13/027 , G05D1/0088 , G05D1/0214 , G05D1/0221 , G06F9/45533 , G06N3/10
摘要: A model training and implementation pipeline trains models for individual embedded systems. The pipeline iterates through multiple models and estimates the performance of the models. During a model generation stage, the pipeline translates the description of the model together with the model parameters into an intermediate representation in a language that is compatible with a virtual machine. The intermediate representation is agnostic or independent to the configuration of the target platform. During a model performance estimation stage, the pipeline evaluates the performance of the models without training the models. Based on the analysis of the performance of the untrained models, a subset of models is selected. The selected models are then trained and the performance of the trained models are analyzed. Based on the analysis of the performance of the trained models, a single model is selected for deployment to the target platform.
-
公开(公告)号:US20240289285A1
公开(公告)日:2024-08-29
申请号:US18505662
申请日:2023-11-09
申请人: Google LLC
发明人: Dong Hyuk Woo , Ravi Narayanaswami
IPC分类号: G06F13/16 , G06F9/38 , G06F15/76 , G06F17/16 , G06N3/045 , G06N3/063 , G06N3/08 , G06N3/10 , G06N5/04 , G06N20/00 , G06N20/10
CPC分类号: G06F13/1668 , G06F9/38 , G06F15/76 , G06F17/16 , G06N3/045 , G06N3/063 , G06N3/08 , G06N3/10 , G06N5/04 , G06N20/00 , G06N20/10 , Y02D10/00
摘要: A computer-implemented method includes receiving, by a computing device, input activations and determining, by a controller of the computing device, whether each of the input activations has either a zero value or a non-zero value. The method further includes storing, in a memory bank of the computing device, at least one of the input activations. Storing the at least one input activation includes generating an index comprising one or more memory address locations that have input activation values that are non-zero values. The method still further includes providing, by the controller and from the memory bank, at least one input activation onto a data bus that is accessible by one or more units of a computational array. The activations are provided, at least in part, from a memory address location associated with the index.
-
公开(公告)号:US12072799B2
公开(公告)日:2024-08-27
申请号:US18121294
申请日:2023-03-14
申请人: CEREMORPHIC, INC.
发明人: Lizy Kurian John , Venkat Mattela , Heonchul Park
IPC分类号: G06F12/04 , G06N3/0464 , G06N3/10
CPC分类号: G06F12/04 , G06N3/0464 , G06N3/10 , G06F2212/16
摘要: A programmable address generator has an iteration variable generator for generation of an ordered set of iteration variables, which are re-ordered by an iteration variable selection fabric, which delivers the re-ordered iteration variables to one or more address generators. A configurator receives an instruction containing fields which provide configuration constants to the address generator, iteration variable selection fabric, and address generators. After configuration, the address generators provide addresses coupled to a memory. In one example of the invention, the address generators generate an input address, a coefficient address, and an output address for performing convolutional neural network inferences.
-
公开(公告)号:US12056220B2
公开(公告)日:2024-08-06
申请号:US17893648
申请日:2022-08-23
申请人: Ciena Corporation
摘要: The present disclosure relates to systems and methods for embedding concealed meta-data into DNNs. Specifically, the system and method presented consists of receiving a trained neural network that includes one or more layers each having weights. The disclosed process includes transforming at least one layer to a transformed domain, adding information to the layer(s) in the transformed domain, and performing an inverse domain transform on at least one layer such that the layer(s) has new weights with an embedded watermark.
-
-
-
-
-
-
-
-
-