Gradient Episodic Memory for Continual Learning: Difference between revisions
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
= Group Member = | |||
Yu Xuan Lee, | Yu Xuan Lee, | ||
Tsen Yee Heng | Tsen Yee Heng | ||
= Background and Introduction = | |||
Supervised learning consist of a training set <math>D_{tx}=(x_i,y_i)^n_{i=1}</math>, where <math>x_i \in X</math> and <math>y_i \in Y</math>. Empirical Risk Minimization (ERM) is one of the common supervised learning method used to minimize a loss function by having multiple passes over the training set. | Supervised learning consist of a training set <math>D_{tx}=(x_i,y_i)^n_{i=1}</math>, where <math>x_i \in X</math> and <math>y_i \in Y</math>. Empirical Risk Minimization (ERM) is one of the common supervised learning method used to minimize a loss function by having multiple passes over the training set. | ||
| Line 17: | Line 17: | ||
Different to machine learning, datas are being observed sequentially, occurred recurrently, and stored limitedly for learning humans. Thus, the iid assumption is not applicable to ERM. One of the characteristics of ERM is "catastrophic forgetting", which is the problem of recalling past knowledge upon acquiring new ones. To overcome this problem, Gradient Episodic Memory (GEM) is introduced to alleviates forgetting on previous acquired knowledge, while solving new problems more efficiently. | Different to machine learning, datas are being observed sequentially, occurred recurrently, and stored limitedly for learning humans. Thus, the iid assumption is not applicable to ERM. One of the characteristics of ERM is "catastrophic forgetting", which is the problem of recalling past knowledge upon acquiring new ones. To overcome this problem, Gradient Episodic Memory (GEM) is introduced to alleviates forgetting on previous acquired knowledge, while solving new problems more efficiently. | ||
= Framework for Continual Learning = | |||
== Task Descriptor == | |||
Revision as of 01:48, 17 November 2018
Group Member
Yu Xuan Lee, Tsen Yee Heng
Background and Introduction
Supervised learning consist of a training set [math]\displaystyle{ D_{tx}=(x_i,y_i)^n_{i=1} }[/math], where [math]\displaystyle{ x_i \in X }[/math] and [math]\displaystyle{ y_i \in Y }[/math]. Empirical Risk Minimization (ERM) is one of the common supervised learning method used to minimize a loss function by having multiple passes over the training set.
[math]\displaystyle{ \frac{1}{|D_{tr}|}\textstyle \sum_{x_i,y_i} \in D_{tr} \ell (f(x_i),y_i) }[/math]
where [math]\displaystyle{ \ell :\mathcal {Y} \times \mathcal {Y} \to [0, \infty) }[/math]
Different to machine learning, datas are being observed sequentially, occurred recurrently, and stored limitedly for learning humans. Thus, the iid assumption is not applicable to ERM. One of the characteristics of ERM is "catastrophic forgetting", which is the problem of recalling past knowledge upon acquiring new ones. To overcome this problem, Gradient Episodic Memory (GEM) is introduced to alleviates forgetting on previous acquired knowledge, while solving new problems more efficiently.