srinadhu/CS231n srinadhu/CS231n

  • Stars
    star
    40
  • Rank 680,660 (Top 14 %)
  • Language
    Jupyter Notebook
  • Created about 6 years ago
  • Updated about 6 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
srinadhu/CS231n
github

srinadhu

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

My solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition

More Repositories

1

RL_Pacman

Reinforcement Learning in Pacman
Python
11
star
2

CS231n_assignment3

Implemented Vanilla RNN and LSTM networks, combined these with pretrained VGG-16 on ImageNet to build image captioning models on Microsoft COCO dataset. Explored use of image gradients for generating new images and techniques used are Saliency Maps, Fooling Images and Class Visualization. Implemented image Style Transfer technique from 'Image Style Transfer Using Convolutional Neural Networks'. Implemented and trained GAN, LS-GAN and DC-GAN on MNIST dataset to produce images that resemble samples from MNIST, DC-GAN gave best resembling images.
Jupyter Notebook
3
star
3

Gibbs_Sampling

Python code for Gibbs Sampler.
Python
2
star
4

Semantic-Visual-Search

Semantic Visual Search: Given an image, retrieve semantically similar looking images.
Python
2
star
5

adversarial_search

Implemented minimax and expectimax search and designed a evaluation function for Pacman State.
Python
2
star
6

convolutional_nn

Implemented fully-connected DNN of arbitrary depth with Batch Norm and Dropout, three-layer ConvNet with Spatial Batch Norm in NumPy. The update rules used for training are SGD, SGD+Momentum, RMSProp and Adam. Implemented three block ResNet in PyTorch, with 10 epochs of training achieves 73.60% accuracy on test set.
Jupyter Notebook
2
star
7

SVM

Support Vector Machines Implementation from scratch using simplified SMO algorithm.
Python
1
star
8

Neural-Machine-Translation

Neural Machine Translation (NMT) from Spanish to English. Architecture is Seq2Seq + Multiplicative Attention + Character-level conditional English (target) language model.
Python
1
star