A growing body of work studies how to answer a question or verify a claim by generating a natural language "proof": a chain of deductive inferences yielding the answer based on a set of premises. However, these methods can only make sound deductions when they follow from evidence that is given. We propose a new system that can handle the underspecified setting where not all premises are stated at the outset; that is, additional assumptions need to be materialized to prove a claim. By using a natural language generation model to abductively infer a premise given another premise and a conclusion, we can impute missing pieces of evidence needed for the conclusion to be true. Our system searches over two fringes in a bidirectional fashion, interleaving deductive (forward-chaining) and abductive (backward-chaining) generation steps. We sample multiple possible outputs for each step to achieve coverage of the search space, at the same time ensuring correctness by filtering low-quality generations with a round-trip validation procedure. Results on a modified version of the EntailmentBank dataset and a new dataset called Everyday Norms: Why Not? show that abductive generation with validation can recover premises across in- and out-of-domain settings.

The global degradation of water resources is a matter of great concern, especially for the survival of humanity. The effective monitoring and management of existing water resources is necessary to achieve and maintain optimal water quality. The prediction of the quality of water resources will aid in the timely identification of possible problem areas and thus increase the efficiency of water management. The purpose of this research is to develop a water quality prediction model based on water quality parameters through the application of a specialised recurrent neural network (RNN), Long Short-Term Memory (LSTM) and the use of historical water quality data over several years. Both multivariate single and multiple step LSTM models were developed, using a Rectified Linear Unit (ReLU) activation function and a Root Mean Square Propagation (RMSprop) optimiser was developed. The single step model attained an error of 0.01 mg/L, whilst the multiple step model achieved a Root Mean Squared Error (RMSE) of 0.227 mg/L.

As we saw in the article about improvements in Deep Q Learning, value-based methods have high variability. To reduce this problem, we spoke about using the advantage function instead of the value function. This function will tell us the improvement compared to the average the action taken at that state is. In other words, this function calculates the extra reward I get if I take this action. The extra reward is that beyond the expected value of that state.