BroadReading

Here are lists of some interesting knowledge I picked up in daily study.

Network

Siamese Network

1. siamese network理解
2. Siamese Network & Triplet Loss
3. CNN Architectures: LeNet, AlexNet, VGG, GoogLeNet, ResNet and more ….

Super Resolution GAN

1. Photo-Realistic Single Image Super-Resolution Using a Generative AdversarialNetwork
2. GAN — Super Resolution GAN (SRGAN)
3. ​

Network Visualization

1. Understanding your Convolution network with Visualizations
2. Deep Visualization Toolbox
3. Visualizing and Understanding Convolutional Networks
4. The vanishing gradient problem and ReLUs – a TensorFlow investigation

Fine-tune

1. A Comprehensive guide to Fine-tuning Deep Learning Models in Keras (Part II)
2. How to debug neural networks. Manual
3. ​

GoogLeNet

1. Review: GoogLeNet (Inception v1)— Winner of ILSVRC 2014 (Image Classification)

2. more layers leads to overfitting

   Increasing the number of hidden units and/or layers may lead to overfitting because it will make it easier for the neural network to memorize the training set, that is to learn a function that perfectly separates the training set but that does not generalize to unseen data.

3. PPT

4. keras code

RNN

1. Recurrent Neural Networks

2. RNN Language Modelling with PyTorch — Packed Batching and Tied Weights

3. Word2Vec — a baby step in Deep Learning but a giant leap towards Natural Language Processing

4. Attention models in NLP a quick introduction

5. ​

   ​

Learning Network

Gradient Descent

1. [机器学习] ML重要概念：梯度（Gradient）与梯度下降法（Gradient Descent）
2. ​

GPU

1. Monitor and Improve GPU Usage for Training Deep Learning Models
2. ​

Reinforcement Learning

1. 5 Things You Need to Know about Reinforcement Learning
2. Deep Reinforcement Learning 基础知识（DQN方面）

Video

Classification

1. Introduction to Video Classification

Python

1. 10 Python File System Methods You Should Know
2. ​

Object Detection

1. R-CNN, Fast R-CNN, Faster R-CNN, YOLO — Object Detection Algorithms
2. Faster R-CNN (object detection) implemented by Keras for custom data from Google’s Open Images Dataset V4
3. ​

Segmentation

1. How to do Semantic Segmentation using Deep learning

DeepLearning Framework

Pytorch

1. FINETUNING TORCHVISION MODELS

Keras

Learning Rate

1. Learning Rate Schedules and A daptive Learning Rate Methods for Deep Learning
2. Using Learning Rate Schedules for Deep Learning Models in Python with Keras
3. ​

Algorithm

1. Introduction to Genetic Algorithms — Including Example Code
2. Genetic Algorithm with Knapsack Problem
3. ​

Productivity

1. 有哪些相见恨晚的高效学习方法？
2. ​

Math

1. Bayesian Methods for Hackers
2. Variational Inference