Lecture 7: Convolutional Networks

Показать описание

Lecture 7 moves from fully-connected to convolutional networks by introducing new computational primitives that respect the spatial structure of 2D image data. We discuss convolution layers, which slide a learnable filter over the input data. We discuss pooling layers, which spatially downsample their input data. We then look at normalization layers including batch, layer, and instance normalization, which normalize their input data along different axes and improve training speed.

_________________________________________________________________________________________________

Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks.

Рекомендации по теме

Комментарии

Great lecture for free. Thank you Michigan University and professor Justin.

jhjjjj

Thank you I found answers to the questions that I have been looking for long time

temurochilov

Amazing!
Pd: Although I am sorry for the guy with the coughing

tatianabellagio

I have this great package for my university course.❤

alokoraon

33:10 stride
53:00 batch normalization

hasan

Thank you for exellent video! But I have a question here, at 1:05:42, after layer normalization, every sample in x has shape 1xD, while μ has shape Nx1. How do you perform the subtraction x-μ?

eurekad

Thanks for an excellent video Justin!! I had a quick question on how does the conv. filters change the 3d input into a 2d output

puranjitsingh

at 35:09, the expression for output in case of stride convolution is (W - K + 2P)/S +1...for W=7, K=3, P = (K-1)/2 = 1 & S=2 we get output as (7 - 3 + 2*1)/2 + 1 = 3 +1 = 4 ...however, the slide shows the output as 3x3 instead of 4x4 at the right hand corner... is it correct..?

rajivb

why they don't use batch norm + layer norm together?

intoeleven

1:01:30 what did he mean by “fusing BN with FC layer or Conv layer”?

bibiworm

In Batch Normalization during Test time at 59:52, what are the averaging equations used to average Mean & Std deviation, sigma ..during the lecture some mention is made of exponential mean of Mean vectors & Sigma vectors...please suggest.

rajivb

sounds like someone was building duplo the entire lecture

magic

Lecture 7: Convolutional Networks

Lecture 7: Convolutional Networks

CS231n Winter 2016: Lecture 7: Convolutional Neural Networks

Lecture 7: Convolutional Networks (UMich EECS 498-007)

DNN 2021: Lecture 7 Convolutional Neural Networks

CS231n Lecture 7 - Convolutional Neural Networks

Lecture 7 - Computer Vision, Convolutional Neural Networks

Stanford CS230: Deep Learning | Autumn 2018 | Lecture 7 - Interpretability of Neural Network

DeepRob Lecture 7 - Convolutional Neural Networks

CS231n Winter 2016 Lecture 7 Convolutional Neural Networks LxfUGhug iQ-sHyIqu_S5Ks.mp4

Convolutional Neural Networks | CNN | Kernel | Stride | Padding | Pooling | Flatten | Formula

Lecture 7 - Convolutional Neural Network

DeepNNs 2022: Lecture 7 Convolution in NNs

ANN online lecture 7 - Convolutional Neural Networks.

Programming for AI (AI504, Fall 2020), Practice 7: Convolutional Neural Network

Deep Learning - Lecture 7.4 (Convolutional Neural Networks: Architectures)

MIT 6.S191 (2023): Convolutional Neural Networks

Deep Learning - Lecture 7.2 (Convolutional Neural Networks: Downsampling)

Lecture 7 | Training Neural Networks II

Convolutional Neural Networks in 7 min (summary)

[Part 7] Convolutional Neural Networks

Lecture 7 - Neural Network Abstractions

7. Convolutional Neural Networks

Reservoir Flow Solutions Lecture-7, Convolution. Fluid flow in Petroleum Reservoirs

Lecture 11 Learning in Convolutional Neural Networks