This paper presents a novel network compression framework Kernel Quantization (KQ), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant performance loss. Unlike existing methods struggling with weight bit-length, KQ has the potential in improving the compression ratio by considering the convolution kernel as the quantization unit. Inspired by the evolution from weight pruning to filter pruning, we propose to quantize in both kernel and weight level. Instead of representing each weight parameter with a low-bit index, we learn a kernel codebook and replace all kernels in the convolution layer with corresponding low-bit indexes. Thus, KQ can represent the weight tensor in the convolution layer with low-bit indexes and a kernel codebook with limited size, which enables KQ to achieve significant compression ratio. Then, we conduct a 6-bit parameter quantization on the kernel codebook to further reduce redundancy. Extensive experiments on the ImageNet classification task prove that KQ needs 1.05 and 1.62 bits on average in VGG and ResNet18, respectively, to represent each parameter in the convolution layer and achieves the state-of-the-art compression ratio with little accuracy loss.

Cyber-physical systems (CPS) can benefit by the use of learning enabled components (LECs) such as deep neural networks (DNNs) for perception and desicion making tasks. However, DNNs are typically non-transparent making reasoning about their predictions very difficult, and hence their application to safety-critical systems is very challenging. LECs could be integrated easier into CPS if their predictions could be complemented with a confidence measure that quantifies how much we trust their output. The paper presents an approach for computing confidence bounds based on Inductive Conformal Prediction (ICP). We train a Triplet Network architecture to learn representations of the input data that can be used to estimate the similarity between test examples and examples in the training data set. Then, these representations are used to estimate the confidence of a set predictor based on the DNN architecture used in the triplet based on ICP. The approach is evaluated using a robotic navigation benchmark and the results show that we can computed trusted confidence bounds efficiently in real-time.

Deep neural networks (DNNs) are commonly labelled as black-boxes lacking interpretability; thus, hindering human's understanding of DNNs' behaviors. A need exists to generate a meaningful sequential logic for the production of a specific output. Decision trees exhibit better interpretability and expressive power due to their representation language and the existence of efficient algorithms to generate rules. Growing a decision tree based on the available data could produce larger than necessary trees or trees that do not generalise well. In this paper, we introduce two novel multivariate decision tree (MDT) algorithms for rule extraction from a DNN: an Exact-Convertible Decision Tree (EC-DT) and a Deep C-Net algorithm to transform a neural network with Rectified Linear Unit activation functions into a representative tree which can be used to extract multivariate rules for reasoning. While the EC-DT translates the DNN in a layer-wise manner to represent exactly the decision boundaries implicitly learned by the hidden layers of the network, the Deep C-Net inherits the decompositional approach from EC-DT and combines with a C5 tree learning algorithm to construct the decision rules. The results suggest that while EC-DT is superior in preserving the structure and the accuracy of DNN, C-Net generates the most compact and highly effective trees from DNN. Both proposed MDT algorithms generate rules including combinations of multiple attributes for precise interpretation of decision-making processes.

In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention mechanism. The experimental results for three languages, including morphologically rich Polish and German, show that our model is comparable to or even outperforms state-of-the-art models. In all cases the superiority of models leveraging contextual embeddings is demonstrated. Finally, this work is intended as a step towards introducing a universal, multilingual sentiment classifier.

Human language users easily interpret expressions that describe unfamiliar situations composed from familiar parts ("greet the pink brontosaurus by the ferris wheel"). Modern neural networks, by contrast, struggle to interpret compositions unseen in training. In this paper, we introduce a new benchmark, gSCAN, for evaluating compositional generalization in models of situated language understanding. We take inspiration from standard models of meaning composition in formal linguistics. Going beyond an earlier related benchmark that focused on syntactic aspects of generalization, gSCAN defines a language grounded in the states of a grid world. This allows us to build novel generalization tasks that probe the acquisition of linguistically motivated rules. For example, agents must understand how adjectives such as 'small' are interpreted relative to the current world state or how adverbs such as 'cautiously' combine with new verbs. We test a strong multi-modal baseline model and a state-of-the-art compositional method finding that, in most cases, they fail dramatically when generalization requires systematic compositional rules.

In topology optimization using deep learning, load and boundary conditions represented as vectors or sparse matrices often miss the opportunity to encode a rich view of the design problem, leading to less than ideal generalization results. We propose a new data-driven topology optimization model called TopologyGAN that takes advantage of various physical fields computed on the original, unoptimized material domain, as inputs to the generator of a conditional generative adversarial network (cGAN). Compared to a baseline cGAN, TopologyGAN achieves a nearly $3\times$ reduction in the mean squared error and a $2.5\times$ reduction in the mean absolute error on test problems involving previously unseen boundary conditions. Built on several existing network models, we also introduce a hybrid network called U-SE(Squeeze-and-Excitation)-ResNet for the generator that further increases the overall accuracy. We publicly share our full implementation and trained network.

This is an updated version. The Godfathers of AI and 2018 ACM Turing Award winners Geoffrey Hinton, Yann LeCun, and Yoshua Bengio shared a stage in New York on Sunday night at an event organized by the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020). The trio of researchers have made deep neural networks a critical component of computing, and in individual talks and a panel discussion they discussed their views on current challenges facing deep learning and where it should be heading. Introduced in the mid 1980s, deep learning gained traction in the AI community the early 2000s. The year 2012 saw the publication of the CVPR paper Multi-column Deep Neural Networks for Image Classification, which showed how max-pooling CNNs on GPUs could dramatically improve performance on many vision benchmarks; while a similar system introduced months later by Hinton and a University of Toronto team won the large-scale ImageNet competition by a significant margin over shallow machine learning methods. These events are regarded by many as the beginning of a deep learning revolution that has transformed AI.

NexOptic Technology Corp., reports that it has made significant advancements to its cutting-edge artificial intelligence (AI) imaging solution. NexOptic's Advanced Low Light Imaging Solution (ALLIS) provides immediate solutions to problems that have plagued the imaging industry for decades. NexOptic's engineered AI drastically reduces image noise common to all imaging systems while improving performance in low light conditions. This is accomplished with NexOptic's expanding suite of patent-pending, deep learning algorithms. Some of the key benefits of ALLIS include: improved low-light performance; dramatic reduction in image noise; improved downstream applications (computational imaging, facial recognition); enhanced long-range image stabilization; major reduction in file sizes.

Google's DeepMind just shared AI-generated predictions about the coronavirus that could help researchers stem the global outbreak

Asking machines to make music by themselves is kind of a strange notion. They don't feel happy or hurt, and as far as we know, they don't long for the affections of other machines. Humans like to think of music as being a strictly human thing, a passionate undertaking so nuanced and emotion-based that a machine could never begin to understand the feeling that goes into the process of making music, or even the simple enjoyment of it. The idea of humans and machines having a jam session together is even stranger. But oddly enough, the principles of the jam session may be exactly what machines need to begin to understand musical expression.