Deep Learning

12345 members.

Intuition behind concepts. Research paper summaries and discussion. Links to tools, datasets, code and other resources.

Invite Members

Show community info

Ask a question or start a poll…

Link

Poll

CommonLounge is a community of learners who learn together. Get started with the featured resources above, ask questions and discuss related stuff with everyone.

NaN.

tutorial

A Visual Introduction (and Review) of Machine Learning

The following links are extremely well done visualizations which cover the important machine learning concepts. I highly recommend you check it out. In fact, they are the best visualizations of machine learning concepts on the web:

Here is another video by Luis Serrano, one of the course developers of Udacity Machine Learning Engineer Nanodegree. Must watch for beginners, and a helpful review if you have just learnt the core machine learning concepts.

Read more…(108 words)

A Visual Introduction to Machine Learning

http://r2d3.us/visual-intro-to-machine-learning-part-1/

http://r2d3.us/visual-intro-to-machine-learning-part-2/

Category: Deep Learning

Top comments in this discussion

Lucinda Forsythe18w

Very helpful advice in this particular post! It’s the little changes that make the largest changes. Thanks for sharing!

Read more… (19 words)

Read (19 words)

Abdellah Dany1y

Hi,

I would like to mention the well done series of 4 videos by the brilliant 3blue1brown which let you visualize what is mach...

Read more… (44 words)

Read (44 words)

Garrett Irwin1y

Connor, its true that they use different units in the text and the graphs, something I didn't notice earlier, and I see that that can be quite annoying.

However, I found this tutorial to be the simplest an...

Read more… (113 words)

Read more (113 words)

Show 3 more
comments

NaN.

discussion

A Non-Technical Introduction to Machine Learning

Why should I read this, and what will I learn?

Machine learning is a field that threatens to both augment and undermine exactly what it means to be human, and it’s becoming increasingly important that you—yes, you—actually understand it.

I don’t think you should need to have a technical background to know what machine learning is or how it’s done. Too much of the discussion about this field is either too technical or too uninformed, and, through this blog, I hope to level the playing field.

This is for smart, ambitious people who want to know more about machine learning but who don’t care about the esoteric statistical and computational details underlying the field. You don’t need to know any math, statistics, or computer science to read and understand it.

By the end of this post, you’ll:

Understand the basic logical framework of ...

Read more…(4369 words)

Category: Deep Learning

Top comments in this discussion

Balamurugan Kannan35w

Excellent article and stick to it's title to keep it shallow for any audience to grasp the concepts behind ML. Thanks. Is there a next part coming for technical introduction for ML.

Read more… (32 words)

Read more (32 words)

Shubham Kumar1y

Great article, Congrats

Can certainly see a follow up article or a part two, where you could discuss a few other models and also their application...

Read more… (42 words)

Read (42 words)

Noah YonackData Science @ SafeG… · 2y

Thank you for the clarification! Super helpful. To further clarify, a simple linear regression model has the form y = b + mX, whereas a multiple linear regression model has the form y = b + (m...

Read more… (155 words)

Read more (155 words)

Show 1 more
comment

NaN.

tutorial

Perceptron algorithm

Lets say you have a dataset for binary classification. Each data point x has n-dimensions, and the target value is y = 1 or -1 for the two classes.

The perceptron

The perceptron algorithm can be visualized as follows.

For a given data point x, the prediction is simply b...

Read more…(318 words)

Category: Deep Learning

Top comments in this discussion

Alokit Jindal46w

The post can be made better by adding some hands on session for the above algorithm.

Read more… (16 words)

Read (16 words)

Alokit Jindal46w

Yes it can be done , but you need to use another algorithm for it , which is known as Support Vector Machine.

For understanding Support Vector Machines go here

Understanding Support Vector Machine algorithm from ...

Read more… (40 words)

Read more (40 words)

Laura Fee Schneider47w

What is b in your prediction function f(x)? You never define or update it in your pseudocode, or did I miss something?

Read more… (22 words)

Read (22 words)

Show 5 more
comments

4.

discussion

Variational Autoencoders

Variational autoencoders were introduced to efficiently to solve the inference problem in deep generative models. A generative model generates data by sampling as follows: z ~ p(z), x ~ p(x|z). p in this case can be modeled using deep neural networks. But using deep neural networks makes it difficult to infer z, given an x. This paper introduces a novel method based on calculus of variations to approximately infer z given x. The authors start with an intuitive objective to optimize, reduce it to the problem of optimization of a variational lower bound and finally illustrate an example using deep neural networks to model the probability distributions. In contrast to GANs (which can easily diverge even with small variations), variational autoencoders are easier to train. Similar to GANs, trained variational autoencoders have be used to generate new images and interpolate between images.

Read more…(142 words)

[1312.6114] Auto-Encoding Variational Bayes

https://arxiv.org/abs/1312.6114

Category: Deep Learning

NaN.

discussion

The 9 Deep Learning Papers You Need To Know About (Understanding CNNs Part 3)

Introduction

In this post, we’ll go into summarizing a lot of the new and important developments in the field of computer vision and co...

Read more…(5078 words)

A Beginner's Guide To Understanding Convolutional Neural Networks

https://commonlounge.com/discussion/8c1bbe51d0434044a5490fff56011a52

https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf

Category: Deep Learning

Top comment in this discussion

Kavita RawatMachine Learning and… · 2y

Adit, this series of CNN posts is truly amazing. I already knew quite a bit about CNNs but I decided to read them anyway. Thought I would leave a review and some notes on each one. :)

I was blown away by this part, learnt so much! Again...

Read more… (92 words)

Read more (92 words)

6.

tutorial

Tutorial: Linearly separable data

The idea of linearly separable is easiest to visualize and understand in 2 dimensions. Let the two classes be represented by colors red and green.

A dataset is said to be linearly separable if it is possible to draw a line that can separate the red and green points from each other.

Here are same examples of linearly separable data:

Read more…(192 words)

Category: Deep Learning

Load More