没有合适的资源？快使用搜索试试~ 我知道了~

首页what's wrong with deep learning

what's wrong with deep learning

Yann

Lecun

4星 · 超过85%的资源需积分: 10 106 下载量 122 浏览量更新于2023-03-16 评论收藏 9.98MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

试读

157页

what's wrong with deep learning .yann lecun 写。pdf文档

资源详情

资源评论

资源推荐

Y LeCun

What's Wrong

With

Deep Learning?

Yann LeCun

Facebook AI Research &

Center for Data Science, NYU

yann@cs.nyu.edu

http://yann.lecun.com

Y LeCun

Plan

The motivation for ConvNets and Deep Learning: end-to-end learning

Integrating feature extractor, classifier, contextual post-processor

A bit of archeology: ideas that have been around for a while

Kernels with stride, non-shared local connections, metric learning...

“fully convolutional” training

What's missing from deep learning?

1. Theory

2. Reasoning, structured prediction

3. Memory, short-term/working/episodic memory

4. Unsupervised learning that actually works

Post-

Processor

Low-Level

Features

Classifier

Y LeCun

Deep Learning = Learning Hierarchical Representations

Traditional Pattern Recognition: Fixed/Handcrafted Feature Extractor

Trainable

Classifier

Feature

Extractor

Mainstream Modern Pattern Recognition: Unsupervised mid-level features

Trainable

Classifier

Feature

Extractor

Mid-Level

Features

Deep Learning: Representations are hierarchical and trained

Trainable

Classifier

Low-Level

Features

Mid-Level

Features

High-Level

Features

Y LeCun

Early Hierarchical Feature Models for Vision

[Hubel & Wiesel 1962]:

simple cells detect local features

complex cells “pool” the outputs of simple

cells within a retinotopic neighborhood.

Cognitron & Neocognitron [Fukushima 1974-1982]

pooling

subsampling

“Simple cells”

“Complex

cells”

Multiple

convolutions

Y LeCun

The Mammalian Visual Cortex is Hierarchical

[picture from Simon Thorpe]

[Gallant & Van Essen]

The ventral (recognition) pathway in the visual cortex has multiple stages

Retina - LGN - V1 - V2 - V4 - PIT - AIT ....

Lots of intermediate representations

剩余156页未读，继续阅读

ZzConstantly

2015-09-08

一般并不全

One might expect the parameter to have the type List. That way, it seems likely, you could call it with parameters of type List or List for any class E. Explain carefully what is wrong with this argument and why the type List is used instead.

Now, consider a method with a parameter of type `List<E>`. The following call might seem valid: ``` List<Object> objects = new ArrayList(); foo(objects); ``` However, if `foo` adds an element of ...

what's wrong is it?ModuleNotFoundError: No module named 'torchsparse'

这是一个错误信息，意思是找不到名为“torchsparse”的模块。可能是因为您运行的代码需要这个模块，但您的环境中没有安装它。您可以尝试使用pip安装该模块，命令为：pip install torchsparse。

few-shot-learning

Few-shot learning refers to the ability of a machine learning model to learn new concepts or tasks with only a few examples, typically much fewer than what is required for traditional learning ...

FAILURE: Build failed with an exception. * What went wrong: Execution failed for task ':app:processDebugMainManifest'. > Manifest merger failed with multiple errors, see logs

这个错误通常表示 AndroidManifest.xml 文件存在冲突或错误。你可以尝试以下步骤来解决问题： 1. 检查 AndroidManifest.xml 文件中是否存在错误或冲突。可以将文件与其他项目进行比较，看看是否有任何差异。...

* What went wrong: A problem occurred configuring project ':vitamio'. > Could not create an instance of type com.android.build.api.variant.impl.LibraryVariantBuilderImpl. > Namespace not specified. Please specify a namespace in the module's build.gradl

It seems that you are encountering an issue with configuring the project ':vitamio' in Android Studio. Specifically, the problem is related to creating an instance of type '...

What's you relationship with chatgpt

As an AI language model developed by OpenAI, I have no personal relationship with ChatGPT or any other AI language models. However, I share similar capabilities and functions as ChatGPT in terms of ...

Please answer the question with English:what’s SJTU’s scientific achievements nowadays

For example, SJTU researchers have developed a deep learning-based system that can diagnose lung cancer with high accuracy, and they have also made breakthroughs in the development of flexible and ...

Suppose you are working for a fund management company. Knowing that you have learned machine learning, your boss has asked you to write “A Proposal To apply Machine Learning to Algorithmic Trading”. If your proposal is successful, your boss will allow you to lead a team. Therefore, you must explain clearly what you want to achieve with machine learning. What would the company be able to achieve if your proposal is supported? You should explain what support you need from the company. For example, what data must the company acquire? What expertise do you need in your team? To manage expectations, you should clearly state the limitations of your proposed project.

如果您的提案被支持，公司可以实现以下目标：1）使用机器学习技术增强算法交易系统，改善交易精度和收益；2）收集、整理和准备相关数据，例如股票价格、市场情绪、技术指标等；3）招募有专业知识的团队成员，以实现...

* What went wrong: Execution failed for task ':compileJava'.

根据提供的引用内容，可以看出这是Gradle构建工具在编译Java代码时出现了错误。其中，引用和引用都是在执行`:front-core:compileJava`任务时出现了错误。具体的错误信息需要查看更详细的日志才能确定。...

> Configure project : type Jar type JavaExec FAILURE: Build failed with an exception. * What went wrong: Execution failed for task ':compileJava'. > Could not find tools.jar. Please check that E:\JDK contains a valid JDK installation. * Try: Run with --stacktrace option to get the stack trace. Run with --info or --debug option to get more log output. * Get more help at https://help.gradle.org BUILD FAILED in 1s 1 actionable task: 1 executed

这似乎是一个Gradle构建错误，错误消息说找不到tools.jar文件，请检查E：\ JDK。这可能是由于您的Java安装未正确配置或Gradle未正确配置。您可以尝试以下步骤来解决此问题： 1. 确保您已正确安装Java，并且JAVA_...

:-1: error: FAILURE: Build failed with an exception. * What went wrong: Could not receive a message from the daemon. * Try: > Run with --stacktrace option to get the stack trace. > Run with --info or --debug option to get more log output. > Run with --scan to get full insights. * Get more help at https://help.gradle.org

这个错误提示是 Gradle 构建系统的错误信息，它表明 Gradle Daemon 无法正常工作或者与 Gradle Daemon 之间通信出现问题。尝试以下步骤来解决此问题： 1. 清除 Gradle 缓存：在命令行中运行 `./gradlew clean` ...

What is the deep link in android?

在 Android 中，深层链接（Deep Link）是一种链接技术，它可以将用户直接带到应用程序的特定页面，而不是仅仅打开应用程序的主页面。深层链接通常使用统一资源标识符（Uniform Resource Identifier，URI）来实现。...

KIOnoway

粉丝: 78
资源: 25

上传资源快速赚钱

我的内容管理收起

我的资源快来上传第一个资源

我的收益

登录查看自己的收益

我的积分登录查看自己的积分

我的C币登录后查看C币余额

我的收藏

我的下载

下载帮助

会员权益专享

what's wrong with deep learning

评论3

会员权益专享

最新资源

what's wrong with deep learning

评论3

matlab deep learning

MATLAB Deep Learning: With Machine Learning, Neural Networks and A I

Deep Learning with R (MEAP v1)-Manning(2017).pdf

What is callback in deep learning

what is the code of deep learning momentum

What are the general selection models for deep learning? What are the models

What are the specific steps of image segmentation by deep learning

deeplearning code

One might expect the parameter to have the type List. That way, it seems likely, you could call it with parameters of type List or List for any class E. Explain carefully what is wrong with this argument and why the type List is used instead.

what's wrong is it?ModuleNotFoundError: No module named 'torchsparse'

few-shot-learning

FAILURE: Build failed with an exception. * What went wrong: Execution failed for task ':app:processDebugMainManifest'. > Manifest merger failed with multiple errors, see logs

* What went wrong: A problem occurred configuring project ':vitamio'. > Could not create an instance of type com.android.build.api.variant.impl.LibraryVariantBuilderImpl. > Namespace not specified. Please specify a namespace in the module's build.gradl

What's you relationship with chatgpt

Please answer the question with English:what’s SJTU’s scientific achievements nowadays

* What went wrong: Execution failed for task ':compileJava'.

What is the deep link in android?

会员权益专享

最新资源