Quantized MANN (Q-MANN) google
Memory-augmented neural networks (MANNs) refer to a class of neural network models equipped with external memory (such as neural Turing machines and memory networks). These neural networks outperform conventional recurrent neural networks (RNNs) in terms of learning long-term dependency, allowing them to solve intriguing AI tasks that would otherwise be hard to address. This paper concerns the problem of quantizing MANNs. Quantization is known to be effective when we deploy deep models on embedded systems with limited resources. Furthermore, quantization can substantially reduce the energy consumption of the inference procedure. These benefits justify recent developments of quantized multi layer perceptrons, convolutional networks, and RNNs. However, no prior work has reported the successful quantization of MANNs. The in-depth analysis presented here reveals various challenges that do not appear in the quantization of the other networks. Without addressing them properly, quantized MANNs would normally suffer from excessive quantization error which leads to degraded performance. In this paper, we identify memory addressing (specifically, content-based addressing) as the main reason for the performance degradation and propose a robust quantization method for MANNs to address the challenge. In our experiments, we achieved a computation-energy gain of 22x with 8-bit fixed-point and binary quantization compared to the floating-point implementation. Measured on the bAbI dataset, the resulting model, named the quantized MANN (Q-MANN), improved the error rate by 46% and 30% with 8-bit fixed-point and binary quantization, respectively, compared to the MANN quantized using conventional techniques.
“Memory Augmented Neural Network”

Gaussian Naive Bayes google
When dealing with continuous data, a typical assumption is that the continuous values associated with each class are distributed according to a Gaussian distribution. For example, suppose the training data contain a continuous attribute, x. We first segment the data by the class, and then compute the mean and variance of x in each class. …

Network Tikhono google
Recovering a function or high-dimensional parameter vector from indirect measurements is a central task in various scientific areas. Several methods for solving such inverse problems are well developed and well understood. Recently, novel algorithms using deep learning and neural networks for inverse problems appeared. While still in their infancy, these techniques show astonishing performance for applications like low-dose CT or various sparse data problems. However, theoretical results for deep learning in inverse problems are missing so far. In this paper, we establish such a convergence analysis for the proposed NETT (Network Tikhonov) approach to inverse problems. NETT considers regularized solutions having small value of a regularizer defined by a trained neural network. Opposed to existing deep learning approaches, our regularization scheme enforces data consistency also for the actual unknown to be recovered. This is beneficial in case the unknown to be recovered is not sufficiently similar to available training data. We present a complete convergence analysis for NETT, where we derive well-posedness results and quantitative error estimates, and propose a possible strategy for training the regularizer. Numerical results are presented for a tomographic sparse data problem using the $\ell^q$-norm of auto-encoder as trained regularizer, which demonstrate good performance of NETT even for unknowns of different type from the training data. …