信号検出理論の解説 (Signal detection theory, a primer)

Address: [go: up one dir, main page]

Include Form Remove Scripts Accept Cookies Show Images Show Referer Rotate13 Base64 Strip Meta Strip Title Session Cookies

More Web Proxy on the site http://driver.im/

Ad

Ad

Ad

Ad

Ad

Ad

Ad

Ad

Ad

Ad

Ad

Ad

SDT primer

You have a sensor (1D continuous value).
You have to decide which is a signal and which
is a noise, based ...

SDT primer

You have a sensor (1D continuous value).
You have to decide which is a signal and which
is a noise, based ...

1) You collect samples.

1) You collect samples.
2) You set the criteria for optimal discrimination.

1) You collect samples (training data).
2) You set the criteria for optimal discrimination.
3) You classify new data by co...

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

SDT primer

1) You collect samples (training data).
2) You set the criteria for optimal discrimination.
3) You classify te...

1) You collect samples (training data).

1) You collect samples (training data).
2) You set the criteria for optimal discrimination.

1) You collect samples.
2) You set the criteria for optimal discrimination.
3) You classify new data by comparing the sens...

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

3) You classify new data by comparing the sensor value and
the criteria.

Criteria

Recognition model (=> model-free)

Unknown processes
classify
generate with...

Generative model (=> model-based)

Processes with unknown parameters
Noise: N(0,1); Signal: N(d’,1)

...

SDT primer

Processes with unknown parameters
Noise: N(0,1); Signal: N(d’,1)

SDT primer

Processes with unknown parameters
Noise: N(0,1); Signal: N(d’,1)

The sensitivity of the sensor is...

SDT primer

Processes with unknown parameters
Noise: N(0,1); Signal: N(d’,1)

The sensitivity of the sensor is...

By changing criteria

By changing criteria

1) You set a criterion and classify samples.
2) You get the feedback (correct or incorrect).
3) You...

1) You set a criterion and classify samples.

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

signal noise
yes hit ● ○
...

1) You set a criterion and classify samples.
2) You get the feedback (correct or incorrect).
3) You obtain data set 1 (wit...

4) Repeat 1)-3) with different criteria.

4) Repeat 1)-3) with different criteria.

4) Repeat 1)-3) with different criteria.

4) Repeat 1)-3) with different criteria.

4) Repeat 1)-3) with different criteria.

4) Repeat 1)-3) with different criteria.

4) Repeat 1)-3) with different criteria.

4) Repeat 1)-3) with different criteria.

5) You reconstruct the distribution of samples.
6) You estimate d’.

5) You reconstruct the distribution of samples.
6) You estimate d’.

5) You reconstruct the distribution of samples.
6) You estimate d’.

5) You reconstruct the distribution of samples.
6) You estimate d’.

5) You reconstruct the distribution of samples.
6) You estimate d’.

5) You reconstruct the distribution of samples.
6) You estimate d’.

5) You reconstruct the distribution of samples.
6) You estimate d’.

How do you change the criteria?

How do you change the criteria?
1) Confidence rating (Human study)

How do you change the criteria?
1) Confidence rating (Human study)

How do you change the criteria?
1) Confidence rating (Human study)
No Yes

How do you change the criteria?
1) Confidence rating (Human study)
Very sure Sure Uncertain Uncertain Sure Very ...

How do you change the criteria?
1) Confidence rating (Human study)
Very sure Sure Uncertain Uncertain Sure Very ...

How do you change the criteria?
1) Confidence rating (Human study)
Very sure Sure Uncertain Uncertain Sure Very ...

How do you change the criteria?
1) Confidence rating (Human study)
Very sure Sure Uncertain Uncertain Sure Very ...

How do you change the criteria?
1) Confidence rating (Human study)
Very sure Sure Uncertain Uncertain Sure Very ...

How do you change the criteria?
1) Confidence rating (Human study)
Very sure Sure Uncertain Uncertain Sure Very ...

Share SlideShare

Facebook
Twitter
LinkedIn

Embed

Size (px)

Show related SlideShares at end

WordPress Shortcode

Link

Share
Email

総研大講義「#8 盲視の脳内機構」レジメ by Masatoshi Yoshida 6527 views
ギャラガー＆ザハヴィ『現象学的な心』合評会第3報告：神経科学の立場から by Masatoshi Yoshida 10465 views
駒場学部講義総合情報学特論III 「意識の科学的研究 - 盲視を起点に」 by Masatoshi Yoshida 8321 views
広域システム科学特殊講義Ⅴ 「意識の神経科学」ハンドアウト by Masatoshi Yoshida 7174 views
駒場学部講義2015 総合情報学特論III 「意識の神経科学:「気づ... by Masatoshi Yoshida 7733 views
「意識の神経科学と神経現象学」ハンドアウト by Masatoshi Yoshida 10460 views

Top clipped slide

View on SlideShare

1 of 111 Ad

1 of 111 Ad