每年有两个版本,您可能会发现它查尔lenging to keep up with the latest features.* In fact, some people who work here feel the same way! This release, I asked the Product Managers about the new features related to deep learning that they think you should know about in release 20a. Here are their responses:

Deep Learning

从深度学习工具箱开始，在20A中有三个新功能要激发。

1. Experiment Manager(new) - A new app that keeps track all conditions when training neural networks. This can be extremely helpful to keep track of all training parameters, data and accuracy of each iteration of the network. More to come on this feature in future posts!
2. Deep Network Designer（更新） - 从应用程序生成MATLAB代码，并直接在应用程序中培训网络。
3. 训练后量化（新） - 这个新视频描述MATLAB中的量化工作流程。

有新的示例突出这些新功能：

• 火车有条件的甘斯
• 使用注意力的训练图像字幕网络
• 使用深度学习的多标签文本分类: This example shows how to classify text data that has multiple independent labels.
• Compare Layer Weight Initializers：此示例显示了如何使用不同重量初始化器训练深度学习网络。
• 具有多个输出的火车网络：此示例显示了如何使用多个输出来训练深度学习网络，这些输出既可以预测手写数字的旋转的标签和角度。

代码生成

GPU Coder

• 万博1manbetx支持许多新网络，包括SSD，双向和状态LSTMS，DarkNet，Inception-Resnet-V2，Nasnet-large和Nasnet-Mobile
• New examples include:
  • 使用单镜头多伯克斯检测器，用于对象检测的代码生成- 这显示了针对Cudnn的SSD网络的代码生成工作流程
  • 代码生成for a Sequence-to-Sequence LSTM Network- This is an updated example which shows code generation for Stateful LSTM

MATLAB编码器

• Support for new networks including:
  • LSTM for ARM CPUs
  • Darknet-19，Darknet-53，Densenet-2011，Inpection-Resnet-V2，Nasnet-large，Nasnet-Mobile，Resnet-18和Intel＆Arm Cpus的X CPUS

信号和音频

信号处理

• 新的独立Signal Labeler app标记信号数据集。您可以在示例中看到它标签信号属性，感兴趣的区域和点
• NewSignalDatastoreto train networks with large collections of signals or signal features across memory and disk. See how it can be used with .MAT files in the example使用深度学习的波形细分
• Many additional signal processing and wavelet functions for feature extraction and time-frequency transformation like频谱图，，，，stft， 或者CWTnow support gpuArrays for GPU acceleration, tall arrays for operating out of memory, and automatic CUDA code generation for running embedded GPUs. See for exampleGPU Acceleration of Scalograms for Deep Learning
• 其他新的深度学习示例，包括迭代方法以减少人为努力创建标记的信号集，，，，which uses a train-as-you-label iterative method for deep learning classifier training

Audio Processing

• 展示如何训练和评估的新示例用于生成合成音频的gan。这突出了深度学习工具箱中最近发布的API，其中包括自定义培训循环
• New example discussing the use ofI-vectors for Speaker Verification。I-vectors are a very popular modern feature often used on audio signals. They are used with deep networks as well as with more traditional machine learning algorithms in lightweight embedded systems
• NewdetectSpeechfunction to automatically detect and annotate regions of speech in audio recordings
• Newtext2speechfunction to generate pre-labeled synthetic speech data using web services, including Google's very popular Wavenet

• GPU加速mfccandMelspectrogram。mfccnow also supports generating CUDA code.

Image Processing

有个新样式转移演示available in Image Processing Toolbox. This demo will walk through the entire process of creating a network designed to take an image and transform it into the style of a reference image. Now you can create images in the style of Picasso, van Gogh, or your favorite artist. The incorporation of custom training loops (Advanced Deep Learning: Key Terms)使诸如样式转移之类的技术相对直观地实现。

对于计算机视觉，有一个新示例描述如何创建单个射击检测器（SSD）。

强化学习

20a release of Reinforcement Learning Toolbox comes with a new agent, Twin Delayed Deep Deterministic Policy Gradient (TD3), additional support for continuous action spaces from existing agents (Policy Gradient, Actor Critic and Proximal Policy Optimization agent) and new examples that showcase how to build custom training algorithms and imitation learning.

• 训练DDPG代理商具有预审前的演员网络
  Reinforcement learning is a data hungry technique that requires many simulations for training. This example shows how to reduce training time, by initializing the neural network policy using existing data and supervised learning.
• 使用自定义培训循环的火车加强学习政策
  While Reinforcement Learning Toolbox includes a variety of popular algorithms to train your system, you may want to customize these algorithms or create your own. This example shows the steps you need to follow to create a custom training algorithm with Reinforcement Learning Toolbox.

Radar & Comms

20a release is exciting for the Radar/Comms area primarily because we have 4 new shipping examples. Here are the latest examples and features available in 20a:

RF Fingerprinting:

• //www.tianjin-qmedu.com/help/comm/examples/design-a-deep-neural-network-with-simulated-data-to-detect-wlan-router-impersonation.html
• //www.tianjin-qmedu.com/help/comm/examples/test-a-deep-neural-network-with-captured-data-to-detect-wlan-router-impersonation.html

5G Channel estimation:

• //www.tianjin-qmedu.com/help/5g/examples/deep-learning-data-synthesis-for-5g-channel-estimation.html

通信通道的对数可能估计

• //www.tianjin-qmedu.com/help/comm/examples/training-and-testing-a-neural-network-for-llr-estimation.html

According to Product Manager, Rick Gentile, "My personal favorites are the examples in links 1 and 2 because we have been getting so many requests for this type of application (RF Fingerprinting). It is a hot topic because it is used to prevent comms network spoofing. The 2^ndexample highlights the work we did with synthesized data using data we collected from a radio."

这篇文章就是这样。希望我们强调了您不知道的新功能和示例。您如何看待清单？任何要添加的东西 - 在下面发表评论！

*您可能还知道20A于3月发布，因此我显然发现跟上最新功能的挑战！我终于升级了，您也应该！