Lambda网络-Pytorch λ网络的实现，这是ImageNet上达到SOTA的一种新的图像识别方法。 新方法利用λ层，该层通过将上下文转换为称为lambda的线性函数并将这些线性函数分别应用于每个输入来捕获交互。 安装 $ pip install lambda-networks 用法 全球背景 import torch from lambda_networks import LambdaLayer layer = LambdaLayer ( dim = 32 , # channels going in dim_out = 32 , # channels

This book explains why AI is unique, what legal and ethical problems it could cause, and how we can address them. It argues that AI is unlike is any other previous technology, owing to its ability to take decisions independently and unpredictably. This gives rise to three issues: responsibility―who is liable if AI causes harm; rights―the disputed moral and pragmatic grounds for granting AI legal personality; and the ethics surrounding the decision-making of AI. The book suggests that in order to address these questions we need to develop new institutions and regulations on a cross-industry and international level. Incorporating clear explanations of complex topics, Robot Rules will appeal to a multi-disciplinary audience, from those with an interest in law, politics and philosophy, to computer programming, engineering and neuroscience.

两个法国RL大牛所写的经典强化学习Tutorial，算法理论介绍相当严格，文献总结全面

使用深度学习（Tensorflow，Tensorflow lite，TensorRT和OpenVINO）在CPU，GPU，VPU和FPGA上实现世界上最快的ANPR / ALPR实现。 多操作系统（NVIDIA Jetson，Android，Raspberry Pi，Linux，Windows）和多Arch（ARM，x86）。 入门Android示例应用程序Benchmark（Java）VideoParallel（Java）VideoSequential（Java）ImageSnap（Java）尝试示例使用Java API将SDK添加到项目中Raspberry Pi（Raspbian OS），Linux，NVIDIA Jetson，Windows等应用程序基准（C ++）识别器（C ++，C＃，Java和Python）使用C ++ API获取帮助，网址为https://www.doubango.org/webapps/alpr/的在线Web演示，网址为https：//www.SDK .doubango.or

Artificial Intelligence A Modern Approach Second Edition Stuart J. Russell and Peter Norvig

Artificial Intelligence - A Modern Approach 3rd ed - S. Russell, P. Norvig

派托奇的SIREN SIREN-Pytorch实现。 安装 $ pip install siren-pytorch 用法 基于SIREN的多层神经网络 import torch from torch import nn from siren_pytorch import SirenNet net = SirenNet ( dim_in = 2 , # input dimension, ex. 2d coor dim_hidden = 256 , # hidden dimension dim_out = 3 , # output dimension, ex. rgb value num_layers = 5 ,

语音情感分析仪 基于长期短期记忆（LSTM）网络的语音情感分析器。 该模型可以有效地分析愤怒，厌恶，恐惧，幸福，中立，悲伤和惊奇的7种基本情绪。 在多伦多情感言语集（TESS）数据集上进行了培训。 这对模型的可推广性造成了一些固有的限制。 由于TESS目前只有两名女性配音演员，并且在录音室中进行录制，因此该模型无法与直接制作相提并论。 该代码在jupyternotebook文件中，并且记录充分。

Table of ContentsGetting Started with Mobile TensorFlowRecognizing Dog Breed or Flower Type Detecting Objects and their LocationsTransforming Pictures with Amazing Art Styles Understanding Simple Speech CommandsDescribing Images in Natural Language Generating Natural Sounding SpeechClassifying and Summarizing TextPerforming Machine Translation from English to FrenchPredicting House and Stock PricesBuilding AlphaGo-like Chess AppSeeing, Listening, Speaking and Learning on Raspberry Pi

人工智能必读书籍，是南安普顿大学人工智能方向MSC前期必读书籍