geektutu / Interview Questions
Licence: mit
机器学习/深度学习/Python/Go语言面试题笔试题(Machine learning Deep Learning Python and Golang Interview Questions)
Stars: ✭ 462
Projects that are alternatives of or similar to Interview Questions
Coding Ninjas Data Structures And Algorithms In Python
Solved problems and assignments of DSA course taught by Coding Ninjas team
Stars: ✭ 70 (-84.85%)
Mutual labels: jupyter-notebook, interview-questions
Quant Notes
Quantitative Interview Preparation Guide, updated version here ==>
Stars: ✭ 180 (-61.04%)
Mutual labels: jupyter-notebook, interview-questions
120 Ds Interview Questions
My Answer to 120 Data Science Interview Questions
Stars: ✭ 304 (-34.2%)
Mutual labels: jupyter-notebook, interview-questions
Sde Interview Questions
Most comprehensive list 📋 of tech interview questions 📘 of companies scraped from Geeksforgeeks, CareerCup and Glassdoor.
Stars: ✭ 5,406 (+1070.13%)
Mutual labels: interview-questions
Automated Feature Engineering
Automated feature engineering in Python with Featuretools
Stars: ✭ 458 (-0.87%)
Mutual labels: jupyter-notebook
Timeseries seq2seq
This repo aims to be a useful collection of notebooks/code for understanding and implementing seq2seq neural networks for time series forecasting. Networks are constructed with keras/tensorflow.
Stars: ✭ 462 (+0%)
Mutual labels: jupyter-notebook
Algorithms and data structures
180+ Algorithm & Data Structure Problems using C++
Stars: ✭ 4,667 (+910.17%)
Mutual labels: interview-questions
Deep Learning Traffic Lights
Code and files of the deep learning model used to win the Nexar Traffic Light Recognition challenge
Stars: ✭ 457 (-1.08%)
Mutual labels: jupyter-notebook
Rl Book
Source codes for the book "Reinforcement Learning: Theory and Python Implementation"
Stars: ✭ 464 (+0.43%)
Mutual labels: jupyter-notebook
Generative Adversarial Network Tutorial
Tutorial on creating your own GAN in Tensorflow
Stars: ✭ 461 (-0.22%)
Mutual labels: jupyter-notebook
Gantts
PyTorch implementation of GAN-based text-to-speech synthesis and voice conversion (VC)
Stars: ✭ 460 (-0.43%)
Mutual labels: jupyter-notebook
Fastquant
fastquant — Backtest and optimize your trading strategies with only 3 lines of code!
Stars: ✭ 457 (-1.08%)
Mutual labels: jupyter-notebook
Neural Turing Machines
Attempt at implementing system described in "Neural Turing Machines." by Graves, Alex, Greg Wayne, and Ivo Danihelka. (http://arxiv.org/abs/1410.5401)
Stars: ✭ 462 (+0%)
Mutual labels: jupyter-notebook
Hyperparameter Optimization
Implementation of Bayesian Hyperparameter Optimization of Machine Learning Algorithms
Stars: ✭ 457 (-1.08%)
Mutual labels: jupyter-notebook
Urban Sound Classification
Urban sound classification using Deep Learning
Stars: ✭ 456 (-1.3%)
Mutual labels: jupyter-notebook
Udacity Deep Learning
Udacity Deep Learning MOOC assignments
Stars: ✭ 463 (+0.22%)
Mutual labels: jupyter-notebook
Artificial Intelligence For Trading
Content for Udacity's AI in Trading NanoDegree.
Stars: ✭ 459 (-0.65%)
Mutual labels: jupyter-notebook
Pba
Efficient Learning of Augmentation Policy Schedules
Stars: ✭ 461 (-0.22%)
Mutual labels: jupyter-notebook
机器学习&编程面试笔试题
序言
持续整理、更新Python、机器学习(Machine Learning)、深度学习(Deep Learning)领域的面试笔试题(interview questions)。
声明：所有习题系博主花费大量精力整理，请尊重劳动成果，未经许可，禁止原文转载。
目录
机器学习
Go 语言
相关链接
选择题示例
使用决策树分类时，如果输入的某个特征的值是连续的，通常使用二分法对连续属性离散化，即根据是否大于/小于某个阈值进行划分。如果采用多路划分，每个出现的值都划分为一个分支，这种方式的最大问题是：
- A 计算量太大
- B 训练集和测试集表现都很差
- C 训练集表现良好，测试集表现差
- D 训练集表现差，测试集表现良好
答案
C 连续值通常采用二分法，离散特征通常采用多路划分的方法，但分支数不宜过多。 连续特征每个值都划分为一个分支，容易过拟合，泛化能力差，导致训练集表现好，测试集表现差。
对神经网络(neural network)而言，哪一项对过拟合(overfitting)和欠拟合(underfitting)影响最大。
- A 隐藏层节点(hidden nodes)数量
- B 学习速率(learning rate)
- C 初始权重
- D 每一次训练的输入个数固定
答案
A 过拟合和欠拟合与神经网络的复杂程度有关，模型越大越容易过拟合。隐藏层节点数量直接决定了模型的大小与复杂程度。
问答题示例
经验误差(empirical error)与泛化误差(generalization error)分别指？
答案
经验误差: 也叫训练误差(training error)，模型在训练集上的误差。
泛化误差: 模型在新样本集(测试集)上的误差。
简述 K折交叉验证(k-fold crossValidation)。
答案
- 数据集大小为N，分成K份，则每份含有样本N/K个。每次选择其中1份作为测试集，另外K-1份作为训练集，共K种情况。
- 在每种情况中，训练集训练模型，用测试集测试模型，计算模型的泛化误差。
- 将K种情况下，模型的泛化误差取均值，得到模型最终的泛化误差。
附：题目主要来源
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].