[MINI] One Shot Learning
Data Skeptic22 Sep 2017

[MINI] One Shot Learning

One Shot Learning is the class of machine learning procedures that focuses learning something from a small number of examples. This is in contrast to "traditional" machine learning which typically requires a very large training set to build a reasonable model.

In this episode, Kyle presents a coded message to Linhda who is able to recognize that many of these new symbols created are likely to be the same symbol, despite having extremely few examples of each. Why can the human brain recognize a new symbol with relative ease while most machine learning algorithms require large training data? We discuss some of the reasons why and approaches to One Shot Learning.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(601)

deepjazz

deepjazz

Deepjazz is a project from Ji-Sung Kim, a computer science student at Princeton University. It is built using Theano, Keras, music21, and Evan Chow's project jazzml. Deepjazz is a computational music ...

29 Apr 201629min

[MINI] Auto-correlative functions and correlograms

[MINI] Auto-correlative functions and correlograms

When working with time series data, there are a number of important diagnostics one should consider to help understand more about the data. The auto-correlative function, plotted as a correlogram, hel...

22 Apr 201614min

Early Identification of Violent Criminal Gang Members

Early Identification of Violent Criminal Gang Members

This week I spoke with Elham Shaabani and Paulo Shakarian (@PauloShakASU) about their recent paper Early Identification of Violent Criminal Gang Members (also available onarXiv). In this paper, they u...

15 Apr 201627min

[MINI] Fractional Factorial Design

[MINI] Fractional Factorial Design

A dinner party at Data Skeptic HQ helps teach the uses of fractional factorial design for studying 2-way interactions.

8 Apr 201611min

Machine Learning Done Wrong

Machine Learning Done Wrong

Cheng-tao Chu (@chengtao_chu) joins us this week to discuss his perspective on common mistakes and pitfalls that are made when doing machine learning. This episode is filled with sage advice for begin...

1 Apr 201625min

Potholes

Potholes

Co-host Linh Da was in a biking accident after hitting a pothole. She sustained an injury that required stitches. This is the story of our quest to file a 311 complaint and track it through the City o...

25 Mar 201641min

[MINI] The Elbow Method

[MINI] The Elbow Method

Certain data mining algorithms (including k-means clustering and k-nearest neighbors) require a user defined parameter k. A user of these algorithms is required to select this value, which raises the ...

18 Mar 201615min

Too Good to be True

Too Good to be True

Today on Data Skeptic, Lachlan Gunn joins us to discuss his recent paper Too Good to be True. This paper highlights a somewhat paradoxical / counterintuitive fact about how unanimity is unexpected in...

11 Mar 201635min

Populært innen Vitenskap

fastlegen
tingenes-tilstand
jss
rss-zahid-ali-hjelper-deg
rekommandert
sinnsyn
rss-paradigmepodden
liberal-halvtime
vett-og-vitenskap-med-gaute-einevoll
forskningno
rss-overskuddsliv
villmarksliv
kvinnehelsepodden
nordnorsk-historie
grunnstoffene
tidlose-historier
rss-inn-til-kjernen-med-sunniva-rose
nevropodden
dekodet-2
rss-rekommandert