机器学习
文章平均质量分 91
王彩旗 edwardwangcq.com
这个作者很懒,什么都没留下…
展开
-
Application example: Photo OCR - Ceiling analysis: What part of the pipeline to work on next
When developing machine learning system, one of the most valuable resource is your time as the developer in terms of picking what to work on next. What you really want to avoid is that spent a lot of time working on some component only to realize, after we原创 2021-05-11 12:29:59 · 128 阅读 · 0 评论 -
Application example: Photo OCR - Getting lots of data: Artificial data synthesis
One of the most reliable ways to get a high performance machine learning system is to take a low bias learning algorithm and to train it on a massive training set. But where did you get so much training data from? It turns out that in machine learning ther原创 2021-05-06 09:49:32 · 285 阅读 · 2 评论 -
Application example: OCR - Sliding windows
In this class, let's talk about how the individual components of photo OCR pipeline works. In particular, we'll center around the discussion of what is called a sliding windows classifier.Figure-1The first stage of photo OCR pipeline is 'Text detection'.原创 2021-04-22 09:32:59 · 127 阅读 · 0 评论 -
Application example: Photo OCR - Problem description and pipeline
We'll talk about phone OCR next for three reasons:Show an example of how a complex machine learning system can be put together Talk about the concept of a machine learning pipeline, and how to allocate resources when try to decide what to do next Tell原创 2021-04-14 09:27:56 · 67 阅读 · 0 评论 -
Large scale machine learning - Map-reduce and data parallelism
In this class, let's talk about a different approach to large scale machine learning called the Map-reduce approach. It is at least as equally important or even more important compared to stochastic gradient descent. By using this idea, you might be able t原创 2021-04-08 08:27:26 · 84 阅读 · 0 评论 -
Large scale machine learning - Online learning
In this class, let's talk about a new large scale machine learning setting called the online learning setting. It allows us to model problems where we have a continuous flood of data coming in and we would like the algorithm to learn form that. Today, many原创 2021-03-29 08:30:09 · 114 阅读 · 0 评论 -
Large scale machine learning - Stochastic gradient descent convergence
In this class, let's talk about:How to make sure the Stochastic gradient descent algorithm is converging well when we're running the algorithm How to tune the learning rate for the algorithm.When we were using batch gradient descent, our standard w.原创 2021-03-23 13:01:52 · 161 阅读 · 0 评论 -
Large scale machine learning - Mini-batch gradient descent
In the previous class, we have talked about Stochastic gradient descent and how it can be faster than Batch gradient descent. In this class, let's talk about Mini-batch gradient descent. It can sometimes work even faster than Stochastic gradient descent.原创 2021-03-21 07:49:22 · 105 阅读 · 0 评论 -
Large scale machine learning - Stochastic gradient descent
In this class, we'll talk about a modification to the basic gradient descent algorithm called Stochastic gradient descent. It will allow us to scale this algorithm to bigger training set.Note that we'll use linear regression as the example, but the idea原创 2021-03-16 18:34:41 · 340 阅读 · 0 评论 -
Large scale machine learning - Learning with large datasets
In next a few classes, we'll talk about large scale machine learning. That is algorithms that dealing with big datasets.Why do we want to use large datasets?Figure-1We've already seen that one of the best ways to get a high performance machine learn.原创 2021-03-11 13:29:55 · 132 阅读 · 0 评论 -
Recommender Systems - Implementational detail: Mean normalization
Let's talk about one implementational detail of Collaborative filtering algorithm: mean normalization. It can sometimes make the algorithm work a little better.MotivationTo motivate the idea of mean normalization, let's consider an example in figure-1原创 2021-03-05 16:04:29 · 109 阅读 · 0 评论 -
Recommender Systems - Vectorization: Low rank matrix factorization
In this class, we'll talk about following 2 things:Vectorization of the Collaborative filtering algorithm One user has recently been looking at one product, can you find other products that are related to this so that you could recommend to the userVec原创 2021-03-03 11:00:48 · 160 阅读 · 0 评论 -
Recommender Systems - Collaborative filtering algorithm
Preview of basic Collaborative filteringIn the last few classes, we know that:If you're given features for movies, you can use that to learn parameters for users figure-1 If you're given parameters for the users, you can use that to learn feature.原创 2021-02-25 16:26:26 · 195 阅读 · 0 评论 -
Recommender Systems - Collaborative filtering
In this class, we'll talk about an approach to build a recommender system that's called collaborative filtering. This algorithm has a very interesting property that it does what is called feature learning. By that I mean it can start to learn for itself wh原创 2021-02-21 13:18:40 · 291 阅读 · 1 评论 -
Recommender Systems - Content-based recommendations
Let's talk about the first approach to build a recommender system: content based recommendations.Suppose we have two features for each movie:: romance (degree of romance): action (degree of action)And as usual, we define Then, each movie can be原创 2021-02-18 17:25:15 · 113 阅读 · 0 评论 -
Recommender Systems - Problem formulation
Let's talk about recommender systems.Motivations to talk about recommender systemsIt's an important application of machine learning Many groups in Silicon Valley now is trying to build better recommender systems. There are many websites or systems in原创 2021-02-09 17:02:39 · 106 阅读 · 0 评论 -
Anomaly detection - Anomaly detection using the multivariate Gaussian distribution
Let's develop a different anomaly detection algorithm based on multivariate Gaussian distribution.Parameters fittingFigure-1The upper part of figure-1 is a recap for definition of multivariate Gaussian distribution. Also it shows a range of different d原创 2021-02-05 11:56:49 · 135 阅读 · 0 评论 -
Anomaly detection - Multivariate Gaussian distribution
Let's talk about one possible extension to the anomaly detection algorithm: Multivariate Gaussian distribution.We'll start with an example of monitoring machines in the data center. If model the two features (CPU load) and (Memory Use) with Gaussian,原创 2021-01-25 12:36:44 · 177 阅读 · 2 评论 -
Anomaly detection - Choosing what features to use
todo原创 2021-01-15 11:14:51 · 113 阅读 · 2 评论 -
Anomaly detection - Anomaly detection vs. supervised learning
TODO原创 2021-01-07 12:20:49 · 114 阅读 · 0 评论 -
Anomaly detection - Developing and evaluating an anomaly detection system
Let's talk about the process of how to develop a specific application of anomaly detection to a problem.原创 2021-01-05 12:21:06 · 95 阅读 · 0 评论 -
Anomaly detection - Algorithm
TODO原创 2020-12-29 08:58:18 · 188 阅读 · 0 评论 -
Anomaly detection - Gaussian distribution
Let's talk about the Gaussian distribution which is also called the normal distribution.Say . If is a distributed Gaussian with mean and variance , then it's denoted as: ( distributed as Gaussian which is parameterized by and )Its plot looks li.原创 2020-12-24 09:37:48 · 116 阅读 · 0 评论 -
Anomaly detection - problem motivation
In this next set of videos, we'll talk about a problem called Anomaly Dection. This is a reasonably commonly use type machine learning. One of the interesting aspects is that it's mainly for unsupervised learning problem, but there're some aspects of it th原创 2020-12-23 09:21:15 · 100 阅读 · 0 评论 -
Dimensionality Reduction - Advice for applying PCA
In an earlier video, I had said that PCA can be sometimes used to speed up the running time of a learning algorithm. In this vido, I'd like to explain how to actually do that and try to give some advice about how to apply PCA.Here's how you can use PC.原创 2020-12-21 09:00:01 · 155 阅读 · 0 评论 -
Dimensionality Reduction - Reconstruction from compressed representation
In some of the early videos, I was talking about PCA as a compresion algorithm. You may have, say, a thousand of dimensional data and compress it to a hundred dimensional feature vector. Or have three dimensional data and compres it to a two dimensional re原创 2020-12-16 08:34:45 · 177 阅读 · 0 评论 -
Dimensionality Reduction - Choosing the number of principal components
In the PCA algorithm, we take n dimensional features and reduce them to k dimensional feature representaion. This number k is a parameter原创 2020-12-09 19:16:43 · 182 阅读 · 2 评论 -
Dimensionality Reduction: Principal Component Analysis algorithm
In this video I'd like to tell you about the principal components analysis algorithm. And by the end of this video, you know how to implement PCA for yourself. And use it to reduce the dimension of your data.Before applying PCA, there is a data pre-pr.原创 2020-11-30 18:09:08 · 239 阅读 · 0 评论 -
Dimensionality Reduction - Principle Component Analysis problem formulation
For the problem of dimensionality reduction, by far the most popular and commonly used algorithm is something called principle components analysis or PCA. In this video, I'd like to start to talk about the problem formulation for PCA. In other words let us原创 2020-11-19 17:11:31 · 149 阅读 · 0 评论 -
Dimensionality Reduction - Motivation II: Data Visualization
In the last video, we talked about dimensionality reduction for the purpose of compressing the data. In this vido, let me tell you a second application of dimensionality reduction and that is to visualize the data. For a lot of machine learning application原创 2020-11-16 16:03:17 · 102 阅读 · 0 评论 -
Dimensionality Reduction - Motivation I: Data Compression
In this video, I'd like to start talking about a second type of unsupervised learning problem called dimensionality reduction. There are a couple of different reasons why one might want to do dimensionality reduction. One is data compression. And as we'll原创 2020-11-09 22:36:12 · 97 阅读 · 0 评论 -
Clustering - Choosing the number of clusters
In this video, I'd like to talk about one last detail of K-means clustering which is how to choose the number of clusters or how to choose the value of the parameter capital K. To be honest, there actually isn't a great way of answering this or doing this原创 2020-11-01 17:23:19 · 482 阅读 · 1 评论 -
Clustering - Random initialization
In this video, I'd like to talk about how to initialize K-means. And more importantly, this will lead to a discussion of how to make K-means avoid local otima as well.Here's the K-means clustering algorithm that we talked about earlier.原创 2020-10-26 21:57:14 · 172 阅读 · 0 评论 -
Clustering - Optimization objective
Most of the supervised learning algorithms we've seen, things like linear regression, logistic regression and so on. All of those algorithms have an optimization objective or some cost function that the algorithm was trying to minimize. It turns out that K原创 2020-10-22 20:21:43 · 170 阅读 · 0 评论 -
Clustering - K-means algorithm
In the clustering problem, we are given an unlabeled data set and we would like to have an algorithm automatically group the data into coherent subsets or into coherent clusters for us. The K-means algorithm is by the the most popular, by far the most wide原创 2020-10-20 20:36:40 · 759 阅读 · 0 评论 -
Clustering - Unsupervised learning introduction
In this video, I'd like to start to talk about clustering. This will be exciting because this is our first unsupervised learning algorithm where we learn from unlabeled data instead of from the labeled data. So, what is unsupervised learning?I briefly.原创 2020-10-14 21:24:52 · 183 阅读 · 0 评论 -
Support Vector Machines - Using an SVM
So far we've been talking about SVMs in a fairly abstract level. In this video, I'd like to talk about what you actually need to do in order to run or to use an SVM.The support vector machine algorithm poses a particular optimization problem. But as I.原创 2020-10-13 22:26:49 · 177 阅读 · 0 评论 -
Support Vector Machine - Kernels II
In the last video, we started to talk about the kernels idea and how it can be used to define new features for the support vector machine. In this video, I'd like to throw in some of the missing details and also say a few words about how to use these ideas原创 2020-10-05 15:58:12 · 152 阅读 · 0 评论 -
Support Vector Machine - Kernels I
In this video, I'd like to start adapting support vector machine in order to develop complex nonlinear classifiers. The main technique for doing that is something called kernels. Let's see what this kernels are and how to use them.If you have a traini.原创 2020-10-02 21:15:58 · 144 阅读 · 0 评论 -
Support Vector Machine - The mathematics behind large margin classification
In this video, I'd like to tell you a bit about the math behind large margin classification. This video is optional, so please feel free to skip it. But it may also give you better intuition about how the optimization problem of the SVM, how that leads to原创 2020-09-16 21:39:02 · 196 阅读 · 0 评论