[深度学习] A Face-to-Face Neural Conversation Model

说明： Neural networks have recently become good at engaging in dialog. However, current approaches are based solely on verbal text, lacking the richness of a real face-to-face conversation. We propose a neural conversation model that aims to read and gene
<algofei> 上传 | 大小：967kb

[深度学习] LLVM Backend Turorial

说明： Tutorial: Creating an LLVM Backend for the Cpu0 Architecture
<noahkong> 上传 | 大小：3mb

[深度学习] 3D-RCNN: Instance-level 3D Object Reconstruction via Render-and-Compare

说明： We present a fast inverse-graphics framework for instance-level 3D scene understanding. We train a deep convolutional network that learns to map image regions to the full 3D shape and pose of all object instances in the image. Our method produces a
<algofei> 上传 | 大小：3mb

[深度学习] IBM-人工智能与认知计算

说明： 很不错的报告，大家可以参考一下，相当全面，对于理解认知计算很好
<studypeipei> 上传 | 大小：15mb

[深度学习] 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

说明： Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D
<algofei> 上传 | 大小：616kb

[深度学习] ENN theory

说明： 用遗传算法优化神经网络权重，通过像遗传算法的变异，交叉和遗传来训练参数，从而得出最优的解。相比于传统的梯度下降法，他可以得到更优的解，但是对计算机并行运算能力要求更高。
<weixin_39960221> 上传 | 大小：676kb

[深度学习] 3D Pose Estimation and 3D Model Retrieval for Objects in the Wild

说明： We propose a scalable, efficient and accurate approach to retrieve 3D models for objects in the wild. Our contri- bution is twofold. We first present a 3D pose estimation approach for object categories which significantly outper- forms the state-of-
<algofei> 上传 | 大小：1mb

[深度学习] 3D Object Detection with Latent Support Surfaces

说明： We develop a 3D object detection algorithm that uses latent support surfaces to capture contextual relationships in indoor scenes. Existing 3D representations for RGB-D images capture the local shape and appearance of object categories, but have lim
<algofei> 上传 | 大小：2mb

[深度学习] 3D Human Sensing, Action and Emotion Recognition in Robot Assisted

说明： We introduce new, fine-grained action and emotion recognition tasks defined on non-staged videos, recorded during robot-assisted therapy sessions of children with autism. The tasks present several challenges: a large dataset with long videos, a larg
<algofei> 上传 | 大小：1mb

[深度学习] cvpr18-3D Human Pose Estimation in the Wild by Adversarial Learning

说明： Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DC- NNs). Despite their success on large-scale datasets col- lected in the constrained lab
<algofei> 上传 | 大小：1mb

[深度学习] 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning

说明： Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we pro- pose a multitask framework for jointly 2D and 3D pose estimation from still images an
<algofei> 上传 | 大小：1mb

[深度学习] 机器学习tensorflow源码编译cpu指令mavx2 mess mfma tensorflow-1.8.0-cp36-cp36m-linux_x86_64

说明： bazel build --jvmopt="-server -Xms20480m" -c opt --copt=-msse3 --copt=-msse4.1 --copt=-msse4.2 --copt=-mavx --copt=-mavx2 --copt=-mfma //tensorflow/tools/pip_package:build_pip_package 编译参数 cpu指令
<jie_linux> 上传 | 大小：85mb