Towards reinforcement learning

Towards reinforcement learning

Reinforcement means the act of making something stronger, especially a feeling or an idea. So, what kinds of things do we need to make stronger in reinforcement learning?

2022-09-21

Machine learning Deep learning

reinforcement learning deep reinforcement learning

PhD thinking accumulation 2022 first half year

PhD thinking accumulation 2022 first half year

Robyn said, "Be confused. Confusion is where inspiration comes from." Without a responsible supervisor, I have to do self-supervision. And that's also one of the important reasons I keep focus on the

2022-09-20

Lifetalk

PhD

Curriculum learning imitates human learning order from easier classes to harder classes

Curriculum learning imitates human learning order from easier classes to harder classes

Curriculum learning (CL) is a training strategy that trains a machine learning model from easier data to harder data (with a curriculum), which imitates the meaningful learning order in human curricul

2022-09-20

Machine learning Deep learning

curriculum learning

$Arxiv preprint generation and jounral sharing rules$

Arxiv preprint generation and jounral sharing rules

For a wider impression on the community, we often publish our manuscript to the public (e.g., arxiv) before it is accepted by a journal.

2022-09-20

Scientific Research/科研

scientific research 科研 PhD graduate school plan

MarsLab holes - don't come, please

MarsLab holes - don't come, please

MarsLab is not a place illustrated like its official website. The supervisor doesn't give you any practical suggestions for doing research. This guy hire two PhD students this year for other professor

2022-09-20

Scientific Research/科研 Lifetalk

scientific research 科研 PhD graduate school plan

Object detection and detection heads 2

Object detection and detection heads 2

We are continuing to talk about regression/classification based detection framework.

2022-09-12

Machine learning Deep learning Computer vision

object detection detection heads

Object detection and detection heads

Object detection and detection heads

Object detection has a significant relationship with video analysis and image understanding. Region selection is an essential part of object detection. Usually, we call it a (detection) head to distin

2022-09-09

Machine learning Deep learning Computer vision

object detection detection heads

Classification vs. localisation vs. semantic segmentation vs. instance segmentation

Classification vs. localisation vs. semantic segmentation vs. instance segmentation

I am confused about segmentation, localisation, and tracking from time to time. Therefore, I want to take some notes and summarise the differences among them.

2022-06-04

Machine learning Deep learning

classification localisation segmentation tracking

Self-supervised learning learns representations from the physical nature

Self-supervised learning learns representations from the physical nature

Self-supervised visual representation learning is a method that learns the physical essence of nature objectives. It is a promising subclass of unsupervised learning.

2022-05-29

Machine learning Deep learning

self-supervised nature

Word embedding - Class review

Word embedding - Class review

We use word embedding to feature representation. The contents of the blog are a note rearranging of course Sequence Model.

2022-05-26

Machine learning Deep learning

word embedding representations