CS231n-stanford-Assignment

This repository contains solutions to my assignments of Stanford’s course CS231n: Convolutional Neural Networks for Visual Recognition (2016-winter). Syllabus for the course can be found here .

Assignment #1

• Q1: k-Nearest Neighbor classifier (20 points) --Done
• Q2: Training a Support Vector Machine (25 points)--Done
• Q3: Implement a Softmax classifier (20 points)--Done
• Q4: Two-Layer Neural Network (25 points)--Done
• Q5: Higher Level Representations: Image Features (10 points) --Done

Assignment #2

• Q1: Fully-connected Neural Network (30 points)--Done
• Q2: Batch Normalization (30 points)--Done
• Q3: Dropout (10 points)--Done
• Q4: ConvNet on CIFAR-10 (30 points)--Done

Assignment #3

• Q1: Image Captioning with Vanilla RNNs (40 points)--Done
• Q2: Image Captioning with LSTMs (35 points) —- Not Done
• Q3: Image Gradients: Saliency maps and Fooling Images (10 points)--Done
• Q4: Image Generation: Classes, Inversion, DeepDream (15 points) —- Not Done

Dataset:

• CiFAR-10 : Assignment-I and II.
• MS-COCO : Assignment - III.
• TinyImageNet: Assignment - III. TinyImageNet --> A subset of the ILSVRC-2012 - (Image downsampled to 64x64 pixels)

Being a Non-Stanford student and having limited access to the course content; Atlas, It was painstakingly done.
It was really worth the effort as it greatly improved my insight about deep learning concepts.

BTW, As this was done all by myself without any ones aide. I really appreciate if you spot any errors. kindly, let me know :-)