Difference between revisions of "Team:SEU/Description"

Line 121: Line 121:
 
                                                 <span style="color:#fff">Project</span>
 
                                                 <span style="color:#fff">Project</span>
 
                                                 <h2>Description</h2>
 
                                                 <h2>Description</h2>
−
                                                 <p>This project is based on one of our previously published article [1]. Artificial intelligence is one prevailing research field in recent years, but most of the implementations are on traditional silicon-based computers or chips. Is it possible to use biochemical materials to implement such systems? Our previous paper provides one possible method, but it is validated by only simulations. In this project, we aim to implement such a system in wet experiments. Also, to aid the design of such systems, we will develop a small software to automatically generate required DNA topological structures.</p>
+
                                                 <p>Artificial intelligence is one prevailing research field in recent years due to its successful application in areas like medical care, computer vision and natural language processing. Most of artificial intelligence systems are implemented with silicon-based chips which have high area complexity and power cost when facing large systems. Is it possible to use bio-chemical materials to implement artificial intelligence systems more efficiently?</p>
−
                                                 <p>In our system, the concentrations of some input DNA species will be regarded as the input to the neural network. Some mathematical calculations are performed in solutions (weighted summation, activation, etc.) and the output of the neural network is the concentration of some certain DNA strands, similarly.</p>
+
 
−
                                                 <p>There are various possible applications of this technology. For example, as it utilizes only DNA, a type of bio-friendly material, with small modifications it may be integrated to other biosystems to create biochemistry robots.</p>
+
                                                 <p>In this project, we have employed DNA reactions to implement neural networks which are basic components in artificial intelligence systems. Specifically, using molecular concentrations as input and output signals, we propose and demonstrate computation models for weighted summation (including multiplication and addition) and activation functions (e.g., ReLU and Sigmoid) which are arithmetic operations in neural networks. Also, the classical backpropagation algorithm which is utilized in the training process can be similarly constructed (which has not been studied in molecular computing to our best knowledge). Based on these models, we synthesize basic neural networks with DNA strand displacement reactions.</p>
 +
 
 +
                                                 <p>To help other researchers obtain the proposed DNA-based artificial neural networks, we develop a software tool to automatically generate DNA reaction models and relevant DNA sequences according to the required parameters of neural networks, which may help them with further bio-computer design and bio-robot design. </p>
  
−
                                                <h2>Preliminaries</h2>
 
−
                                                <p>DNA strands have been proved a powerful medium to perform computation. Previous researches [2], [3] have shown some interesting applicatoins of such materials, which implemented a "probabilistic switch" and a pattern recognition machine, respectively.</p>
 
−
                                                <p>In this project, we plan to utilize a similar approach to conduct our experiment, implement a neural network using biochemical materials and validate our previous theory.</p>
 
  
 
                                                 <h2>References</h2>
 
                                                 <h2>References</h2>
−
                                                 <p>[1]C. Fang, Z. Shen, Z. Zhang, X. You and C. Zhang, "Synthesizing a Neuron Using Chemical Reactions," 2018 IEEE International Workshop on Signal Processing Systems (SiPS), Cape Town, 2018, pp. 187-192.</p>
+
                                                 <p>[1]C. Fang, Z. Shen, Z. Zhang, X. You and C. Zhang, "Synthesizing a Neuron Using Chemical Reactions," IEEE International Workshop on Signal Processing Systems (SiPS), Cape Town, 2018, pp. 187-192.</p>
 
                                                 <p></p>
 
                                                 <p></p>
 
                                                 <p>[2]Wilhelm, Daniel, Jehoshua Bruck, and Lulu Qian. "Probabilistic switching circuits in DNA." Proceedings of the National Academy of Sciences 115.5 (2018): 903-908.</p>
 
                                                 <p>[2]Wilhelm, Daniel, Jehoshua Bruck, and Lulu Qian. "Probabilistic switching circuits in DNA." Proceedings of the National Academy of Sciences 115.5 (2018): 903-908.</p>
 
                                                 <p></p>
 
                                                 <p></p>
 
                                                 <p>[3]Cherry, Kevin M., and Lulu Qian. "Scaling up molecular pattern recognition with DNA-based winner-take-all neural networks." Nature 559.7714 (2018): 370.</p>
 
                                                 <p>[3]Cherry, Kevin M., and Lulu Qian. "Scaling up molecular pattern recognition with DNA-based winner-take-all neural networks." Nature 559.7714 (2018): 370.</p>
 +
                                                <p></p>
 +
                                                <p>[4]DNA Strand Displacement, <a href="https://www.youtube.com/watch?v=zjC_0PW9A4c&feature=youtu.be&tdsourcetag=s_pctim_aiomsg">https://www.youtube.com/watch?v=zjC_0PW9A4c&feature=youtu.be&tdsourcetag=s_pctim_aiomsg</a>. </p>
 
                                                 <p></p>
 
                                                 <p></p>
 
                                             </div>
 
                                             </div>

Revision as of 08:12, 1 October 2019

Project

Description

Artificial intelligence is one prevailing research field in recent years due to its successful application in areas like medical care, computer vision and natural language processing. Most of artificial intelligence systems are implemented with silicon-based chips which have high area complexity and power cost when facing large systems. Is it possible to use bio-chemical materials to implement artificial intelligence systems more efficiently?

In this project, we have employed DNA reactions to implement neural networks which are basic components in artificial intelligence systems. Specifically, using molecular concentrations as input and output signals, we propose and demonstrate computation models for weighted summation (including multiplication and addition) and activation functions (e.g., ReLU and Sigmoid) which are arithmetic operations in neural networks. Also, the classical backpropagation algorithm which is utilized in the training process can be similarly constructed (which has not been studied in molecular computing to our best knowledge). Based on these models, we synthesize basic neural networks with DNA strand displacement reactions.

To help other researchers obtain the proposed DNA-based artificial neural networks, we develop a software tool to automatically generate DNA reaction models and relevant DNA sequences according to the required parameters of neural networks, which may help them with further bio-computer design and bio-robot design.

References

[1]C. Fang, Z. Shen, Z. Zhang, X. You and C. Zhang, "Synthesizing a Neuron Using Chemical Reactions," IEEE International Workshop on Signal Processing Systems (SiPS), Cape Town, 2018, pp. 187-192.

[2]Wilhelm, Daniel, Jehoshua Bruck, and Lulu Qian. "Probabilistic switching circuits in DNA." Proceedings of the National Academy of Sciences 115.5 (2018): 903-908.

[3]Cherry, Kevin M., and Lulu Qian. "Scaling up molecular pattern recognition with DNA-based winner-take-all neural networks." Nature 559.7714 (2018): 370.

[4]DNA Strand Displacement, https://www.youtube.com/watch?v=zjC_0PW9A4c&feature=youtu.be&tdsourcetag=s_pctim_aiomsg.