Architecture Today I’d like to share a system architecture for autonomous intelligence proposed by Yann LeCun. The architecture consists of the following modules. Perception Perceive the world through multiple sensors and predict the current state Actor Predicts a sequence of…
Contrastive Learning Contrastive learning is a technique used to optimize computer-vision-related tasks by comparing multiple samples against each other to learn the attribute to identify the difference between each class.
Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. Here is a visual comparison of 4 different Siamese architectures.
Abstract Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. However, previous works include the following that causes all outputs to “collapse” to a constant. Negative Sampling Large Batches Momentum Encoders This paper…
The Three Stage This paper combines SimSiam(a self-supervised learning method to learn feature representations) with active learning to reduce labeling effort in 3 stages. Stage 1 Train the Encoder with all available data Stage 2: Fine-tune the SVM/Classifier layer with…
Best Source To Learning AI: Towards Data Science I’ve been involved in many computer-vision-related projects (Image Classification, Object Detection, Image segmentation, Image generation, etc.) since I’ve been working as an AI engineer, and every single time I always eventually land…
SOM SOM(Self-Organizing map) is a dimensionality reduction method using unsupervised learning that generates a discretized representation of the input data which consists of multiple columns and rows as a “MAP”(Typically 2D).
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.