Home
last modified time | relevance | path

Searched full:neural (Results 1 – 25 of 375) sorted by relevance

12345678910>>...15

/external/googleapis/google/cloud/aiplatform/v1beta1/
Dnas_job.proto36 // Represents a Neural Architecture Search (NAS) job.
129 // The spec of multi-trial Neural Architecture Search (NAS).
159 // Required. The maximum number of Neural Architecture Search (NAS) trials
198 // The Reinforcement Learning Algorithm for Multi-trial Neural
202 // The Grid Search Algorithm for Multi-trial Neural
207 // The multi-trial Neural Architecture Search (NAS) algorithm
225 // The Neural Architecture Search (NAS) algorithm specification.
237 // It defines the search space for Neural Architecture Search (NAS).
243 // The output of a multi-trial Neural Architecture Search (NAS) jobs.
254 // The output of this Neural Architecture Search (NAS) job.
[all …]
/external/google-cloud-java/java-aiplatform/proto-google-cloud-aiplatform-v1beta1/src/main/proto/google/cloud/aiplatform/v1beta1/
Dnas_job.proto36 // Represents a Neural Architecture Search (NAS) job.
129 // The spec of multi-trial Neural Architecture Search (NAS).
159 // Required. The maximum number of Neural Architecture Search (NAS) trials
198 // The Reinforcement Learning Algorithm for Multi-trial Neural
202 // The Grid Search Algorithm for Multi-trial Neural
207 // The multi-trial Neural Architecture Search (NAS) algorithm
225 // The Neural Architecture Search (NAS) algorithm specification.
237 // It defines the search space for Neural Architecture Search (NAS).
243 // The output of a multi-trial Neural Architecture Search (NAS) jobs.
254 // The output of this Neural Architecture Search (NAS) job.
[all …]
/external/googleapis/google/cloud/aiplatform/v1/
Dnas_job.proto36 // Represents a Neural Architecture Search (NAS) job.
129 // The spec of multi-trial Neural Architecture Search (NAS).
159 // Required. The maximum number of Neural Architecture Search (NAS) trials
198 // The Reinforcement Learning Algorithm for Multi-trial Neural
202 // The Grid Search Algorithm for Multi-trial Neural
207 // The multi-trial Neural Architecture Search (NAS) algorithm
225 // The Neural Architecture Search (NAS) algorithm specification.
237 // It defines the search space for Neural Architecture Search (NAS).
243 // The output of a multi-trial Neural Architecture Search (NAS) jobs.
254 // The output of this Neural Architecture Search (NAS) job.
[all …]
/external/google-cloud-java/java-aiplatform/proto-google-cloud-aiplatform-v1/src/main/proto/google/cloud/aiplatform/v1/
Dnas_job.proto36 // Represents a Neural Architecture Search (NAS) job.
129 // The spec of multi-trial Neural Architecture Search (NAS).
159 // Required. The maximum number of Neural Architecture Search (NAS) trials
198 // The Reinforcement Learning Algorithm for Multi-trial Neural
202 // The Grid Search Algorithm for Multi-trial Neural
207 // The multi-trial Neural Architecture Search (NAS) algorithm
225 // The Neural Architecture Search (NAS) algorithm specification.
237 // It defines the search space for Neural Architecture Search (NAS).
243 // The output of a multi-trial Neural Architecture Search (NAS) jobs.
254 // The output of this Neural Architecture Search (NAS) job.
[all …]
/external/armnn/shim/sl/
DREADME.md1 # Arm NN Support Library Neural Networks driver
3 This directory contains the Arm NN Support Library for the Android Neural Networks API.
7 The support library inherits it's parameters from the Arm NN Android Neural Networks driver. Parame…
13 …Setting ARMNN_SL_OPTIONS will pass parameters to the Arm NN Support Library Neural Networks driver.
31 The Arm NN Support Library Neural Networks driver is provided under the [MIT](https://spdx.org/lice…
/external/libopus/dnn/
DREADME.md5 - J.-M. Valin, J. Skoglund, [LPCNet: Improving Neural Speech Synthesis Through Linear Prediction](h…
6 - J.-M. Valin, U. Isik, P. Smaragdis, A. Krishnaswamy, [Neural Speech Synthesis on a Shoestring: Im…
7 - K. Subramani, J.-M. Valin, U. Isik, P. Smaragdis, A. Krishnaswamy, [End-to-end LPCNet: A Neural V…
11 - J.-M. Valin, J. Skoglund, [A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet](https://…
12 - J. Skoglund, J.-M. Valin, [Improving Opus Low Bit Rate Quality with Neural Speech Synthesis](http…
14 …P*, arXiv:2212.04453, 2023. ([blog post](https://www.amazon.science/blog/neural-encoding-enables-m…
124 1. [LPCNet: DSP-Boosted Neural Speech Synthesis](https://people.xiph.org/~jm/demo/lpcnet/)
125 1. [A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet](https://people.xiph.org/~jm/demo/…
/external/tensorflow/tensorflow/core/platform/
Dcpu_info.h121 AVX512_4VNNIW = 36, // Integer neural network (Intel Xeon Phi only)
122 AVX512_4FMAPS = 37, // Floating point neural network (Intel Xeon Phi only)
123 AVX512_VNNI = 38, // Integer neural network
124 AVX512_BF16 = 39, // Bfloat16 neural network
127 AVX_VNNI = 40, // Integer neural network
131 // supporting two popular data types in neural networks, int8 and bfloat16.
/external/tensorflow/tensorflow/lite/nnapi/
DREADME.md1 # Android Neural Network API
3 The Android Neural Networks API (NNAPI) is an Android C API designed for running
9 processors, including dedicated neural network hardware, graphics processing
/external/libpalmrejection/ui/events/ozone/evdev/touch_filter/palm_model/
Donedevice_train_palm_detection_filter_model.h15 // A simplified Neural stylus Palm Detection Model, trained on the data based on
16 // a single device class but translatable to others. Neural inference
17 // implementation based on inline neural net inference.
/external/gemmlowp/doc/
Dpublic.md111 Because gemmlowp is primarily aimed at neural network inference workloads,
118 The rationale is that the LHS is typically the constant weights of a neural
120 multiplication), while the RHS and result are neural network activations,
145 This is useful for some flavors of neural network inference with "per-channel
147 a neural network trained in float arithmetic was subsequently quantized. On the
148 other hand, retraining neural networks for quantized inference tends to remove
Dquantization.md24 principles and some domain-specific knowledge of neural networks, we can arrive
55 Here a domain-specific constrain from neural networks appears: for some neural
259 `[-10,10]` in most neural networks. For example, a neural network using Relu6
340 least in some convolutional neural network applications.
/external/glide/third_party/gif_encoder/
DLICENSE13 NEUQUANT Neural-Net quantization algorithm by Anthony Dekker, 1994. See
14 "Kohonen neural networks for optimal colour quantization" in "Network:
15 Computation in Neural Systems" Vol. 5 (1994) pp 351-367. for a discussion of
/external/XNNPACK/
DREADME.md3 XNNPACK is a highly optimized library of floating-point neural network inference operators for ARM,…
17 XNNPACK implements the following neural network operators:
80 …NDK r21 (`bazel build -c opt --config android_arm64 :end2end_bench`) and neural network models wit…
95 …` on a Raspbian Buster build with CMake (`./scripts/build-local.sh`) and neural network models wit…
105 - Yury Pisarchyk, Juhyun Lee "Efficient Memory Management for Deep Neural Net Inference".
117 - [Samsung ONE (On-device Neural Engine)](https://github.com/Samsung/ONE)
/external/licenseclassifier/v2/assets/License/GIF-Encoder/
Dlicense.txt13 NEUQUANT Neural-Net quantization algorithm by Anthony Dekker, 1994.
14 See "Kohonen neural networks for optimal colour quantization"
15 in "Network: Computation in Neural Systems" Vol. 5 (1994) pp 351-367.
/external/pytorch/torch/nn/modules/
Dpixelshuffle.py20 …Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network`_
47 … Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network:
73 …Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network`_
100 … Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network:
Ddropout.py44 `Improving neural networks by preventing co-adaptation of feature
65 .. _Improving neural networks by preventing co-adaptation of feature
233 More details can be found in the paper `Self-Normalizing Neural Networks`_ .
250 .. _Self-Normalizing Neural Networks: https://arxiv.org/abs/1706.02515
265 can be found in the paper `Self-Normalizing Neural Networks`_ .
299 .. _Self-Normalizing Neural Networks: https://arxiv.org/abs/1706.02515
/external/pytorch/
DREADME.md7 - Deep neural networks built on a tape-based autograd system
17 - [Dynamic Neural Networks: Tape-Based Autograd](#dynamic-neural-networks-tape-based-autograd)
59 | [**torch.nn**](https://pytorch.org/docs/stable/nn.html) | A neural networks library deeply integr…
83 ### Dynamic Neural Networks: Tape-Based Autograd
85 PyTorch has a unique way of building neural networks: using and replaying a tape recorder.
88 One has to build a neural network and reuse the same structure again and again.
108 You can write your new neural network layers in Python itself, using your favorite libraries
124 At the core, its CPU and GPU Tensor and neural network backends
127 Hence, PyTorch is quite fast — whether you run small or large neural networks.
136 Writing new neural network modules, or interfacing with PyTorch's Tensor API was designed to be str…
[all …]
/external/google-cloud-java/java-aiplatform/proto-google-cloud-aiplatform-v1/src/main/java/com/google/cloud/aiplatform/v1/
DNasJobOutputOrBuilder.java30 * Output only. The output of this multi-trial Neural Architecture Search
45 * Output only. The output of this multi-trial Neural Architecture Search
60 * Output only. The output of this multi-trial Neural Architecture Search
/external/google-cloud-java/java-aiplatform/proto-google-cloud-aiplatform-v1beta1/src/main/java/com/google/cloud/aiplatform/v1beta1/
DNasJobOutputOrBuilder.java30 * Output only. The output of this multi-trial Neural Architecture Search
45 * Output only. The output of this multi-trial Neural Architecture Search
60 * Output only. The output of this multi-trial Neural Architecture Search
/external/tensorflow/tensorflow/lite/delegates/gpu/
DREADME.md8 workloads. Thus, they are well-suited for deep neural nets which consists of a
17 quantization of your neural network was not an option due to lower accuracy
18 caused by lost precision, such concern can be discarded when running deep neural
166 * [On-Device Neural Net Inference with Mobile GPUs](https://arxiv.org/abs/1907.01989)
/external/tensorflow/tensorflow/lite/swift/Sources/
DCoreMLDelegate.swift29 /// `neuralEngine` but the device does not have the Neural Engine.
53 /// Enables the delegate for devices with Neural Engine only.
73 /// value is `.neuralEngine` indicating that the delegate is enabled for Neural Engine devices
/external/pytorch/benchmarks/distributed/rpc/parameter_server/trainer/
Dtrainer.py29 A method to be implemented by child class that will train a neural network.
80 their neural network forward.
93 neural network forward.
221 model (nn.Module): neural network model
/external/pytorch/docs/source/notes/
Dmodules.rst6 PyTorch uses modules to represent neural networks. Modules are:
10 easy construction of elaborate, multi-layer neural networks.
77 :ref:`Neural Network Training with Modules`.
125 For example, here's a simple neural network implemented as a custom module:
143 the neural network and are utilized for computation within the module's ``forward()`` method. Immed…
278 These examples show how elaborate neural networks can be formed through module composition and conv…
279 manipulated. To allow for quick and easy construction of neural networks with minimal boilerplate, …
280 …large library of performant modules within the :mod:`torch.nn` namespace that perform common neural
283 In the next section, we give a full example of training a neural network.
288 * Defining neural net modules: https://pytorch.org/tutorials/beginner/examples_nn/polynomial_module…
[all …]
/external/android-nn-driver/
DREADME.md1 # Arm NN Android Neural Networks driver
3 This directory contains the Arm NN driver for the Android Neural Networks API, implementing the and…
/external/tensorflow/tensorflow/lite/g3doc/performance/
Dcoreml_delegate.md17 and later (iPhone Xs and later) to use Neural Engine for faster inference.
58 // Core ML delegate will only be created for devices with Neural Engine
133 ### Using Core ML delegate on devices without Neural Engine
135 By default, Core ML delegate will only be created if the device has Neural
223 determine its Neural Engine availability. See the

12345678910>>...15