We explore the co-relations between Neural systems, CMOS transistors and Hidden Markov Models(HMM). We have built a computational model, implementing an HMM classifier that was built using biophysically based CMOS dendrites for wordspotting. The system was implemented on a reconfigurable analog platform. The system thus realized, was found to have high computational efficiency. We discuss the implications of such a computational model. We will also discuss how analog systems can effectively model biological systems, considering benefits both in terms of cost and power dissipation.We have built a YES/NO wordspotter system, modeled on an HMM classifier using CMOS dendrites. Wordspotting is the detection of specific words in unconstrained speech [1]. The objective was to build computational models using circuits that are biologically inspired. Dendrites have been known to perform computations like coincidence detection [2]. It has been shown mathematically, that dendrites are similar to a continuous-time HMM [3]. We implemented the system on a reconfigurable analog platform, the RASP 2.8a [4]. We will also show experimental results for the same. We will further discuss the advantages of such a system in terms of computational efficiency and the broader impact of such modeling.HMM models are a popular choice for speech recognition systems. They have been known to be highly accurate. However, there is still no solution for wordspotting in unconstrained speech [5], [6]. Now even though digital systems have greater accuracy than analog systems; analog systems have lower power consumption. This is closer to how biological systems function. Also, speech is analog in nature. Thus for certain applications especially implantable devices, an analog system is preferred [7]. Previously analog systems were not used much as they were neither programmable nor reconfigurable. However now that we have programmable/reconfigurable analog systems, building larger bio-inspired systems has become a reality.In section 1 we will overview the inter-relation between the fields of Neural systems, CMOS transistors and HMMs. In section 2 we will discuss the HMM classifier model and discuss the experimental results seen. In section 3 we will give a brief overview of the tools used. In section 4 we will compare the computational efficiency of the analog HMM classifier. In section 5 we will talk about the broader impact of this hypothesis and future directions in this research. BIOLOGY Fig. 1.The diagram depicts the intersection between the fields of Neuro-biology, Hidden Markov Models and CMOS transistors. We have demonstrated in the past how we can build reconfigurable dendrites using programmable analog techniques. We have also shown how such a dendritic network can be used to build an HMM classifier which is typically used for speech recognition systems. Thus it is reasonable to believe that one can compare a HMM network with a group of cortical cells. The co-relations between these two areas is significant for many applications such as lowpow...