Deep Text Retrieval Models based on DNN, CNN, RNN and Transformer: A review

Liu, Jianping; Chu, Xintao; Wang, Yingfei; Wang, Meng

doi:10.1109/ccis57298.2022.10016379

Cited by 2 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there has been a growing interest in connecting images and text to facilitate tasks such as image retrieval [1,2], text retrieval [3], and content-based image classification [2,4]. This interest stems from the fact that images and text are two fundamental modalities for representing and communicating information and combining them can provide richer and more informative representations [5].…”

Section: Introductionmentioning

confidence: 99%

Image-Text Connection: Exploring the Expansion of the Diversity Within Joint Feature Space Similarity Scores

Mohammadi,

Eftekhari,

Hassani

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Image-Text Connection: Exploring the Expansion of the Diversity Within Joint Feature Space Similarity Scores

Mohammadi,

Eftekhari,

Hassani

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

Neuromorphic one-shot learning utilizing a phase-transition material

Galloni,

Yuan,

Zhu

et al. 2024

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Design of hardware based on biological principles of neuronal computation and plasticity in the brain is a leading approach to realizing energy- and sample-efficient AI and learning machines. An important factor in selection of the hardware building blocks is the identification of candidate materials with physical properties suitable to emulate the large dynamic ranges and varied timescales of neuronal signaling. Previous work has shown that the all-or-none spiking behavior of neurons can be mimicked by threshold switches utilizing material phase transitions. Here, we demonstrate that devices based on a prototypical metal-insulator-transition material, vanadium dioxide (VO 2 ), can be dynamically controlled to access a continuum of intermediate resistance states. Furthermore, the timescale of their intrinsic relaxation can be configured to match a range of biologically relevant timescales from milliseconds to seconds. We exploit these device properties to emulate three aspects of neuronal analog computation: fast (~1 ms) spiking in a neuronal soma compartment, slow (~100 ms) spiking in a dendritic compartment, and ultraslow (~1 s) biochemical signaling involved in temporal credit assignment for a recently discovered biological mechanism of one-shot learning. Simulations show that an artificial neural network using properties of VO 2 devices to control an agent navigating a spatial environment can learn an efficient path to a reward in up to fourfold fewer trials than standard methods. The phase relaxations described in our study may be engineered in a variety of materials and can be controlled by thermal, electrical, or optical stimuli, suggesting further opportunities to emulate biological learning in neuromorphic hardware.

show abstract

Deep Text Retrieval Models based on DNN, CNN, RNN and Transformer: A review

Cited by 2 publications

References 48 publications

Image-Text Connection: Exploring the Expansion of the Diversity Within Joint Feature Space Similarity Scores

Image-Text Connection: Exploring the Expansion of the Diversity Within Joint Feature Space Similarity Scores

Neuromorphic one-shot learning utilizing a phase-transition material

Contact Info

Product

Resources

About