In this letter a new active element the Current Follower Transconductance Amplifier (CFTA) for the realization of the current-mode analog blocks is presented. The element is a combination of the Current Follower (CF) and the Balanced Output Transconductance Amplifier (BOTA). Possible internal structure of the CFTA is presented. The usage of the new active element is shown on the design of the Kerwin-Huelsman-Newcomb (KHN) structure working in the current mode. The frequency filter using the CFTA elements has been designed using the signal-flow graphs. The circuit structure employs three CFTA elements and two grounded passive elements. The filter enables realizing not only the basic functions as the low- (LP), band- (BP) and high-pass (HP) but also the notch and all-pass (AP) filter. The advantage of the structure presented is that the outputs of the filter are at high impedance and hence it is not necessary to use other auxiliary active elements. The properties of the filter proposed were verified by sensitivity and AC analyses in the PSPICE program.

In this paper, a dynamic constructive algorithm for fault tolerant feedforward neural network, called DCFTA, is proposed. The algorithm starts with a network with single hidden neuron, and a new hidden unit is added dynamically to the network whenever it fails to converge. Before inserting the new hidden neuron into the network, only the weights connecting the new hidden neuron to the other neurons are trained (i. e. , updated) until there is no significant reduction of the output error. To generate a fault tolerant network, the relevance of each synaptic weight is estimated in each cycle, and only the weights which have their relevance less than a specified threshold are updated in that cycle. The loss of a connections between neurons (which are equivalent to stuck-at-0 faults) are assumed. The simulation results indicate that the network constructed by DCFTA has a significant fault tolerance ability.