Creating My Own Deepfake: A $552 Experiment

Creating My Own Deepfake: A $552 Experiment

Deepfake technology uses deep neural networks to replace a face in a video with another face. This realistic technology has potential for misuse, yet it is becoming increasingly popular. In this article, I will take a close look at the technology itself by creating my own work to answer: How does Deepfake software work? How … Read more

Understanding Backpropagation in Deep Learning

Understanding Backpropagation in Deep Learning

This article is a translated note of the Stanford University CS231N course, authorized by Professor Andrej Karpathy of Stanford University. This is a work of Big Data Digest, and unauthorized reproduction is prohibited. For specific requirements for reproduction, see the end of the article. Sign up now Machine Learning Training Registration is now open! Top-notch … Read more

Unlocking Creativity: Computer Vision Software for Lego

Unlocking Creativity: Computer Vision Software for Lego

Produced by Big Data Digest Author: Caleb When it comes to Lego, it’s a toy loved by both adults and children. Every time I see a pile of Lego bricks and piece them together to form a template, the sense of achievement is off the charts. After finishing, I also want to display the creation … Read more

Getting Started with PyTorch: A Powerful Deep Learning Framework

Getting Started with PyTorch: A Powerful Deep Learning Framework

PyTorch is a powerful deep learning framework that has become quite popular! Whether you’re working on computer vision or natural language processing, it can be extremely useful. Today, let’s discuss some basics of PyTorch and see why it is so well-loved. Tensors: The Core of PyTorch 1. A tensor is the basic data structure in … Read more

Introducing PyTorch’s New Tool: MM for 3D Visualization of Matrix Multiplication and Transformer Attention

Introducing PyTorch's New Tool: MM for 3D Visualization of Matrix Multiplication and Transformer Attention

Click belowCard, follow the “CVer” public account AI/CV heavy content delivered instantly Click to enter—>【Computer Vision and Transformer】Group Chat Reprinted from: New Intelligence | Edited by:Peach 【Guide】The latest 3D visualization tool “mm” launched by the PyTorch team can simulate the matrix multiplication of the real world. The simulated world in the matrix is really here. … Read more

Implement Handwritten Digit Recognition with PyTorch

Implement Handwritten Digit Recognition with PyTorch

Hello everyone! I’m Dog Brother. Today, we are going to explore a super interesting project together: implementing handwritten digit recognition using PyTorch! This project will not only help us understand the basics of deep learning but also allow us to build a neural network model from scratch. I will guide you step by step in … Read more

Innovative Network Structures of Convolutional Neural Networks

Innovative Network Structures of Convolutional Neural Networks

Follow the official account “ML_NLP“ Set as “Starred“, heavy content delivered first time! As a major part of deep learning, model architecture has always been a hot topic of research. Besides AutoML technology, what are some unconventional and innovative network architectures? 1 Author: Yan You San Source: https://www.zhihu.com/question/337470480/answer/766380855This article has been authorized for reprint by … Read more

Understanding Convolutional Neural Networks (CNN)

Understanding Convolutional Neural Networks (CNN)

Brothers, today we are going to talk about a particularly “high-end” but actually very practical and interesting technology – Convolutional Neural Networks (CNN). Don’t be afraid, the name sounds quite intimidating, but actually, if we chat in plain language, you will find that, hey, this thing is not that difficult! First, we need to understand … Read more

Research on Electromagnetic Signal Recognition Based on CNN-Transformer Fusion Model

Research on Electromagnetic Signal Recognition Based on CNN-Transformer Fusion Model

Abstract: With the rapid development of communication technology today, the electromagnetic space environment has become increasingly complex, and the types of signals in the electromagnetic space have also diversified. Faced with various interferences in the electromagnetic space, accurately and effectively distinguishing the types of electromagnetic signals has become more challenging. To address this issue, a … Read more

Explaining CNNs From the Frequency Domain Perspective

Explaining CNNs From the Frequency Domain Perspective

↑ ClickBlue Text Follow the Jishi Platform This article is authorized by Zhihu Q&A, reprinting requires authorization from the original author. Editor丨Jishi Platform Jishi Guide How to think about and explain convolutional neural networks from the perspective of the frequency domain? This article整理了两则优质回答,希望能给大家带来启发。>> Join the Jishi CV technology exchange group and stay at the forefront … Read more