This is my personal blog about many things that could range from things like Computer Science to personal experiences and thoughts.
If you have any questions or find any inaccuracies in my explanations or my notes please let me know.
Blog
-
Understand the intuition behind working of filters/kernels in CNNs
In this blog ill try to explain my understanding and intuition about the working of filters/kernels in CNNs. Suppose we take an RGB (3 channels) image of the number 7 and we are trying to identify what is the number by using CNNs then we apply a filter/kernel to it that gives us an output… Read more
Clubs
Santa Cruz Artificial Intelligence:
02/24/2020: Neural Networks workshop presentation
Research
Augmented Design Lab: October 2019 – January 2020
Argo.ai’s Argoverse research presentation
Individual Work
deeplearning.ai Courses: August – September 2019
#1 Neural Networks and Deep Learning
Week 1 & 2 – Classification, Logistic Regression, Cost Function
Week 3 – NN, Vectorization, Activation functions, Gradient Descent
Week 4 – DNNs, Forward Prop, Back Prop, Hyperparameters
#2 Improving Deep Neural Networks
Week 1 – Train/ Dev/ Test set, Bias & Variance, Regularization, Overfitting, Dropout, Data Augmentation, Early Stopping, Vanishing/ Exploding gradients, Weight initialization
Week 2 – Batch vs Mini-Batch gradient descent, Exponentially Weighted Averages, Bias Correction, Momentum, RMSprop, Adam Optimization Algorithm, Hyperparameter choices, Learning Rate Decay, Local Optima Problem
Week 3 – Tuning Hyperparaemters, Batch Normalization, Batch Norm in NN, Softmax Regression, Training Softmax
#3 Structuring Machine Learning Projects
Week 1 – Orthogonolization, Single Number Evaluation Metric, Setting up train/ dev/ test/ set
Week 2 – Error Analysis, Cleaning up incorrectly labelled data, correcting incorrect Dev/ Test set examples, Training and Testing & Bias and Variance, Data Mismatch Problem, Transfer Learning, Multi-task learning, End-to-end Deep Learning
#4 Convolutional Neural Networks
Week 1 – Convolutional Operation, edge detection, Padding, Strided Convolutions, Multiple Filters, Max Pooling, Average Pooling, personal explanation and interpretation
Week 2 – Different types of CNNs – LeNet-5, Alex Net, VGG-16, Residual Networks, Residual Block, Networks in Networks, 1×1 Convolutions, Inception Module
Week 3 – Object Localization, Classification with localization, Landmark Detection, Sliding Windows Detection, CNN implementation of Sliding Windows, YOLO algorithm, Intersection over Union (IoU), Non-max Supression, Anchor Box Algorithm, Region Proposals – R-CNNs, Fast R-CNNs, Faster R-CNNs
Week 4 – Face verification vs Face recognition, similarity function, Siamese Network, Triplet Loss, Face verification & Binary Classification, Neural Style Transfer, Content Cost function, Style Cost Function