Challenges of Auto-Driving One of the challenges of auto-driving is avoiding collisions. The vehicles on the road will have to observe each other’s speed, position, braking/acceleration, and many other elements. Collaborative autonomous driving tackles this challenge. This technique gathers information…
Opening Morphology Erode Image Dilate Back Image Code: import cv2 import numpy as np img = cv2.imread(“img_path”) kernel = np.ones((5,5),np.uint8) opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel) Closing Morphology Dilate Image Erode Back Image Code: import cv2 import numpy as np img…
Improving A3C Deep Reinforcement Learning Model In case you don’t know what an A3C model is, please check my previous post. By replacing the hidden layer with an LSTM layer, you can improve the performance of the A3C model.
A3C: Asynchronous Advantage Actor-Critic A3C is a deep reinforcement learning method that consists of mainly 3 elements. Element 1: Asynchronous Instead of only having one agent trying to get to the desired destination, this paper has multiple agents exploring the…
Eligibility Trace Let’s say we want to use Q-Learning(a reinforcement learning method) to have an agent get from point A to a certain destination. Without Eligibility Trace, the agent will take one step and get feedback as a “REWARD” to…
Intuition Deep Convolutional Q-Learning is a reinforcement learning method that visually perceives an image to understand what to do next to maximize the reward to achieve a certain task. Let’s say we are playing Mario. We can use DCQLearning to…
ONNX Due to the increase of frameworks for developing machine learning models, working across frameworks and hardware ecosystems became extremely difficult. ONNX (Open Neural Network eXchange) is an open-source standard that defines a common set of operators and a file…
NNs and GNNs NN’s Expects inputs as a node GNN’s Inputs/Outputs graphs instead of a singular node. Expects inputs as an array of nodes. Considers “Adjacency Matrix” which stores information on the relationships between each node, besides the results from…
Findings for Tabular Medium-sized Datasets While deep learning has enabled tremendous progress on text and image datasets, results show that tree-based models remain state-of-the-art on tabular medium-sized data(~10K samples). Finding 1: NNs are biased to overly smooth solutions. NN’s struggle…
Otsu Binarization Image thresholding is used during the preprocessing phase to binarize images depending on the pixel intensities. Otsu Binarization is one method to find the appropriate threshold by minimizing the variance between each class. Here is an implementation example…