Various embodiments are generally directed to techniques for determining artificial neural network topologies, such as by utilizing probabilistic graphical models, for instance. Some embodiments are particularly related to determining neural network topologies by bootstrapping a graph, such as a probabilistic graphical model, into a multi-graphical model, or graphical model tree. Various embodiments may include logic to determine a collection of sample sets from a dataset. In various such embodiments, each sample set may be drawn randomly for the dataset with replacement between drawings. In some embodiments, logic may partition a graph into multiple subgraph sets based on each of the sample sets. In several embodiments, the multiple subgraph sets may be scored, such as with Bayesian statistics, and selected amongst as part of determining a topology for a neural network.

Various embodiments are generally directed to techniques for determining artificial neural network topologies, such as by utilizing probabilistic graphical models, for instance. Some embodiments are particularly related to determining neural network topologies by bootstrapping a graph, such as a probabilistic graphical model, into a multi-graphical model, or graphical model tree. Various embodiments may include logic to determine a collection of sample sets from a dataset. In various such embodiments, each sample set may be drawn randomly for the dataset with replacement between drawings. In some embodiments, logic may partition a graph into multiple subgraph sets based on each of the sample sets. In several embodiments, the multiple subgraph sets may be scored, such as with Bayesian statistics, and selected amongst as part of determining a topology for a neural network.

The invention discloses a deep network lung texture recognition method combined with multi-scale attention, which belongs to the field of image processing and computer vision. In order to accurately recognize the typical texture of diffuse lung disease in computed tomography (CT) images of the lung, a unique attention mechanism module and multi-scale feature fusion module were designed to construct a deep convolutional neural network combing multi-scale and attention, which achieves high-precision automatic recognition of typical textures of diffuse lung diseases. In addition, the proposed network structure is clear, easy to construct, and easy to implement.

A method for determining the state of a system among a plurality of states, includes acquiring values of a reference physical quantity of the system corresponding to a plurality of points in an original space, each value being paired with one point of the plurality of points and with one state of the system; embedding a portion of the points in a representation space, the representation space being in bijection with a sub-variety of the original space, each point in the representation space being paired with one state; determining a pairing function that pairs any position of the original space with a position in the representation space; determining the position in the representation space of a point of the original space paired with an acquired value, and determining the state of the system from the position of the point paired with the acquired value in the representation space.

An artificial intelligence-based system comprises an input preparation module that accesses a sequence database and generates an input base sequence. The input base sequence comprises a target base sequence with target bases, wherein the target base sequence is flanked by a right base sequence with downstream context bases, and a left base sequence with upstream context bases. A sequence-to-sequence model processes the input base sequence and generates an alternative representation of the input base sequence. An output module processes the alternative representation of the input base sequence and produces at least one per-base output for each of the target bases in the target base sequence. The per-base output specifies, for a corresponding target base, signal levels of a plurality of epigenetic tracks.

A method and system for determining an access score is disclosed. The method includes receiving an access request to access a resource by a user device. Next, a user embedding is retrieved from an embedding table, the user embedding associated with a user identifier of the user device and providing a multidimensional data point that represents a context of a user identifier. The context may correspond to the user identifier appearing in previous access requests within temporal proximity to other access requests from a subset of other user devices among a plurality of user devices. The method then inputs the user embedding into a first machine learning model that is trained based at least in part on the embedding table. The first machine learning model subsequently outputs an access score that corresponds to a level of authenticity of authorizing the user device to access the resource.

A system and method apply an input noisy ultrasonic test (UT) scan image to an input layer of a convolutional neural network, generate a feature map using a convolutional layer, pool the feature map using a pooling layer, apply the pooled feature map to a fully connected layer, generate a de-noised UT scan image, and output the de-noised UT scan image from an output layer.

Certain aspects of the present disclosure provide techniques for residual normalization. A first tensor comprising a frequency dimension and a temporal dimension is accessed. A second tensor is generated by applying a frequency-based instance normalization operation to the first tensor, comprising, for each respective frequency bin in the frequency dimension, computing a respective frequency-specific mean of the first tensor. A third tensor is generated by: scaling the first tensor by a scale value, and aggregating the scaled first tensor and the second tensor. The third tensor is provided as input to a layer of a neural network.

Methods and systems for performing transfer learning with basis scaling and pruning. One method includes obtaining a pre-trained deep convolutional neural network (DCNN), decomposing each weight matrix of the DCNN, and decomposing each convolutional layer by applying the respective decomposed weight matrix to the convolution layer to form a first layer which comprises the left matrix for convolution, and a second layer which comprises the right matrix for convolution. The method also includes providing a basis-scaling convolutional layer having a weight matrix that is derived by a function of singular values and the right singular vectors and training the basis scaling factors of the basis-scaling convolutional layers.

Disclosed are various embodiments of systems and methods of deep learning for colorectal polyp screening and providing a prediction of neoplasticity of a polyp. A video of a colonoscopy procedure can be captured. Frames from the video or images associated with the colonoscopy procedure can be extracted. A model for classifying objects that appear in the frames or the images can be obtained. A classification can be determined for a polyp that appears in at least one of the frames or images based on applying the frames or images to an input layer of the model.