Qianli Liao

2.0k citations
26 papers · 725 indexed · 1 hit paper · h-index 11

Qianli Liao

23 papers receiving 702 citations

Hit Papers

Why and when can deep-but not shallow-networks avoid the ...3042017202620202023100200300

Peers

Qianli Liao
Comparison fields: 5 of 115
  • Artificial Intelligence 337
  • Computational Mathematics 6
  • Statistical and Nonlinear Physics 109
  • Computer Vision and Pattern Recognition 156
  • Cognitive Neuroscience 112
Replace Botond Cseke with:
Botond Cseke Netherlands
Olivier Breuleux Canada
Michaël Mathieu United States
Judith Bütepage Sweden
Dorina Thanou Switzerland
Benjamin Ricaud Switzerland
Yanyang Xiao China
Chong‐Jin Ong Singapore
GE Hinton Canada
Qianli Liao relative to Botond Cseke Netherlands Botond Cseke's profile →
Citations per field
00.5×7.3×
Botond Cseke · 1×
Citations per year

Countries citing papers authored by Qianli Liao

Since Specialization
Citations

This map shows the geographic impact of Qianli Liao's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Qianli Liao with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Qianli Liao more than expected).

Fields of papers citing papers by Qianli Liao

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Qianli Liao. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Qianli Liao. The network helps show where Qianli Liao may publish in the future.

Co-authorship network

The 23 scholars most cited alongside Qianli Liao, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Qianli Liao Line = papers co-authored together Qianli Liao links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown
#Work
1 20250
2 20239
3 202014
4
Implicit dynamic regularization in deep networks
20200
5 202084
6
Theory III: Dynamics and Generalization in Deep Networks -- a simple solution
20192
7 20185
8
Biologically-Plausible Learning Algorithms Can Scale to Large Datasets
20180
9 201814
10
When Is Handcrafting Not a Curse
20181
11 2017108
12 20165
13
Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality
20163
14 201634
15
Learning Real and Boolean Functions: When Is Deep Better Than Shallow
201620
16 201650
17 20163
18 201523
19
Subtasks of Unconstrained Face Recognition
20149
20
Learning invariant representations and applications to face verification
201319

About Qianli Liao

Qianli Liao is a scholar working on Computational Mathematics, Artificial Intelligence and Computer Vision and Pattern Recognition, having authored 26 papers that have together received 725 indexed citations. Recurring topics across this work include Neural Networks and Applications (9 papers), Sparse and Compressive Sensing Techniques (7 papers), Stochastic Gradient Optimization Techniques (7 papers), Face and Expression Recognition (4 papers), Face Recognition and Perception (3 papers), Machine Learning and Algorithms (3 papers), Machine Learning and ELM (3 papers) and Domain Adaptation and Few-Shot Learning (3 papers). The work is most often cited by research in Artificial Intelligence (337 citations), Computational Mathematics (6 citations) and Statistical and Nonlinear Physics (109 citations). Qianli Liao has collaborated with scholars based in United States, Italy and China. Frequent co-authors include Tomaso Poggio, H. N. Mhaskar, Brando Miranda, Lorenzo Rosasco, Joel Z. Leibo, Fabio Anselmi, Winrich A. Freiwald, Vijay Chandrasekhar, Mengjia Xu and Jie Lin. Their work appears in journals such as Bulletin of the Polish Academy of Sciences Technical Sciences, IEEE Transactions on Consumer Electronics, Nature Communications, Current Biology and PLoS Computational Biology.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026