The first "template" vector is During training and evaluation, T is randomly drawn from 1 to 10 in the task. We use three feedforward controller networks coupled with our memory network. For our simulations with BAM, we follow the same controller set-up as above. Unlike in the original work, there is no LSTM controller or reinforcement learning component. There is a reader network and a writer network for the read and write operations respectively.

Associative networks theory is increasingly providing tools to interpret update rules of artificial neural networks. At the same time, deriving neural learning rules from a solid theory remains a fundamental challenge. We make some steps in this direction by considering general energy-based associative networks of continuous neurons and synapses that evolve in multiple time scales. We use the separation of these timescales to recover a limit in which the activation of the neurons, the energy of the system and the neural dynamics can all be recovered from a generating function. By allowing the generating function to depend on memories, we recover the conventional Hebbian modeling choice for the interaction strength between neurons. Finally, we propose and discuss a dynamics of memories that enables us to include learning in this framework.

We propose a novel perspective of the attention mechanism by reinventing it as a memory architecture for neural networks, namely Neural Attention Memory (NAM). NAM is a memory structure that is both readable and writable via differentiable linear algebra operations. We explore three use cases of NAM: memory-augmented neural network (MANN), few-shot learning, and efficient long-range attention. First, we design two NAM-based MANNs of Long Short-term Memory (LSAM) and NAM Turing Machine (NAM-TM) that show better computational powers in algorithmic zero-shot generalization tasks compared to other baselines such as differentiable neural computer (DNC). Next, we apply NAM to the N-way K-shot learning task and show that it is more effective at reducing false positives compared to the baseline cosine classifier. Finally, we implement an efficient Transformer with NAM and evaluate it with long-range arena tasks to show that NAM can be an efficient and effective alternative for scaled dot-product attention.

Multivariate long sequence time-series forecasting (M-LSTF) is a practical but challenging problem. Unlike traditional timer-series forecasting tasks, M-LSTF tasks are more challenging from two aspects: 1) M-LSTF models need to learn time-series patterns both within and between multiple time features; 2) Under the rolling forecasting setting, the similarity between two consecutive training samples increases with the increasing prediction length, which makes models more prone to overfitting. In this paper, we propose a generalizable memory-driven Transformer to target M-LSTF problems. Specifically, we first propose a global-level memory component to drive the forecasting procedure by integrating multiple time-series features. In addition, we adopt a progressive fashion to train our model to increase its generalizability, in which we gradually introduce Bernoulli noises to training samples. Extensive experiments have been performed on five different datasets across multiple fields. Experimental results demonstrate that our approach can be seamlessly plugged into varying Transformer-based models to improve their performances up to roughly 30%. Particularly, this is the first work to specifically focus on the M-LSTF tasks to the best of our knowledge.

In recent years, online ride-hailing platforms have become an indispensable part of urban transportation. After a passenger is matched up with a driver by the platform, both the passenger and the driver have the freedom to simply accept or cancel a ride with one click. Hence, accurately predicting whether a passenger-driver pair is a good match turns out to be crucial for ride-hailing platforms to devise instant order assignments. However, since the users of ride-hailing platforms consist of two parties, decision-making needs to simultaneously account for the dynamics from both the driver and the passenger sides. This makes it more challenging than traditional online advertising tasks. Moreover, the amount of available data is severely imbalanced across different cities, creating difficulties for training an accurate model for smaller cities with scarce data. Though a sophisticated neural network architecture can help improve the prediction accuracy under data scarcity, the overly complex design will impede the model's capacity of delivering timely predictions in a production environment. In the paper, to accurately predict the MSR of passenger-driver, we propose the Multi-View model (MV) which comprehensively learns the interactions among the dynamic features of the passenger, driver, trip order, as well as context. Regarding the data imbalance problem, we further design the Knowledge Distillation framework (KD) to supplement the model's predictive power for smaller cities using the knowledge from cities with denser data and also generate a simple model to support efficient deployment. Finally, we conduct extensive experiments on real-world datasets from several different cities, which demonstrates the superiority of our solution.

A common challenge for most current recommender systems is the cold-start problem. Due to the lack of user-item interactions, the fine-tuned recommender systems are unable to handle situations with new users or new items. Recently, some works introduce the meta-optimization idea into the recommendation scenarios, i.e. predicting the user preference by only a few of past interacted items. The core idea is learning a global sharing initialization parameter for all users and then learning the local parameters for each user separately. However, most meta-learning based recommendation approaches adopt model-agnostic meta-learning for parameter initialization, where the global sharing parameter may lead the model into local optima for some users. In this paper, we design two memory matrices that can store task-specific memories and feature-specific memories. Specifically, the feature-specific memories are used to guide the model with personalized parameter initialization, while the task-specific memories are used to guide the model fast predicting the user preference. And we adopt a meta-optimization approach for optimizing the proposed method. We test the model on two widely used recommendation datasets and consider four cold-start situations. The experimental results show the effectiveness of the proposed methods.

This code tries to implement the Neural Turing Machine, as found in https://arxiv.org/abs/1410.5401, as a backend neutral recurrent keras layer. A very default experiment, the copy task, is provided, too. In the end there is a TODO-List. Having tensorflow-gpu is recommend, as everything is about 20x faster. In my case this experiment takes about 100 minutes on a NVIDIA GTX 1050 Ti.

I've found that the overwhelming majority of online information on artificial intelligence research falls into one of two categories: the first is aimed at explaining advances to lay audiences, and the second is aimed at explaining advances to other researchers. I haven't found a good resource for people with a technical background who are unfamiliar with the more advanced concepts and are looking for someone to fill them in. This is my attempt to bridge that gap, by providing approachable yet (relatively) detailed explanations. In this post, I explain the titular paper - Neural Turing Machines. I initially didn't intend to cover this paper, but another paper that I did want to cover wasn't making any sense to me, and since it used a modification of the NTM architecture, I decided to make sure that I really understood NTMs before moving on.

When analyzing the genome, researchers have discovered that proteins bind to DNA based on certain patterns of the DNA sequence known as "motifs". However, it is difficult to manually construct motifs due to their complexity. Recently, externally learned memory models have proven to be effective methods for reasoning over inputs and supporting sets. In this work, we present memory matching networks (MMN) for classifying DNA sequences as protein binding sites. Our model learns a memory bank of encoded motifs, which are dynamic memory modules, and then matches a new test sequence to each of the motifs to classify the sequence as a binding or nonbinding site.