Abstract: A method for rehearsal-free continual learning includes obtaining a set of training samples where training sample in the set of training samples is associated with a respective task of a plurality of different tasks. The method includes obtaining a task-invariant prompt representative of learned knowledge common to each respective task of the plurality of different tasks. The method includes, for each respective task of the plurality of different tasks, obtaining a respective task-specific prompt representative of learned knowledge specific to the respective task. The method includes, during each of one or more training iterations, for each respective training sample in the set of training samples, selecting the respective task-specific prompt representative of the respective task of the respective training sample and training a model using the task-invariant prompt and the selected respective task-specific prompt.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing retrosynthesis using a neural network. One of the methods includes generating a prediction of a set of a plurality of predicted reactants that are combinable to generate a target compound, the generating comprising processing, for each of a plurality of candidate sets of reactants, a network input characterizing the candidate set using a neural network, determining, for each candidate set of the plurality of candidate sets, a score using the generated probabilities; and selecting a particular candidate set of one or more reactants using the determined scores.

Abstract: The present disclosure provides a computer-implemented method for determining an optimized list of sets of hyperparameter values for application to an additional machine learning task. The method includes obtaining data describing a plurality of different machine learning tasks. The method includes obtaining a plurality of candidate sets of hyperparameter values. The method includes determining an ordered list of sets of hyperparameters selected from the plurality of candidate sets of hyperparameter values, wherein the ordered list of sets of hyperparameters minimizes an aggregate loss over the plurality of different machine learning tasks. The method includes storing the ordered list of sets of hyperparameters for use in training an additional machine learning model to perform an additional machine learning task.

Abstract: An endoscope system includes an endoscope, a display device, and a cable interconnecting the endoscope and the display device. The endoscope includes an elongated body extending distally from a handle. An image sensor is disposed within a distal portion of the elongated body, a lens is disposed at a distal end of the elongated body, and a light source including one or more light emitting elements is integrated into the distal end of the elongated body and positioned radially outward of the lens. An integrated processor is disposed within the handle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises generating a distance map for a given protein, wherein the given protein is defined by a sequence of amino acid residues arranged in a structure, wherein the distance map characterizes estimated distances between the amino acid residues in the structure, comprising: generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein the first positions are a proper subset of the sequence; and generating the distance map for the given protein using the plurality of distance map crops.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction and protein domain segmentation. In one aspect, a method comprises generating a plurality of predicted structures of a protein, wherein generating a predicted structure of the protein comprises: updating initial values of a plurality of structure parameters of the protein, comprising, at each of a plurality of update iterations: determining a gradient of a quality score for the current values of the structure parameters with respect to the current values of the structure parameters; and updating the current values of the structure parameters using the gradient.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises, at each of one or more iterations: determining an alternative predicted structure of a given protein defined by alternative values of structure parameters; processing, using a geometry neural network, a network input comprising: (i) a representation of a sequence of amino acid residues in the given protein, and (ii) the alternative values of the structure parameters, to generate an output characterizing an alternative geometry score that is an estimate of a similarity measure between the alternative predicted structure and the actual structure of the given protein.

Abstract: An endoscope system includes an endoscope, a display device, and a cable interconnecting the endoscope and the display device. The endoscope includes an elongated body extending distally from a handle. An image sensor is disposed within a distal portion of the elongated body, a lens is disposed at a distal end of the elongated body, and a light source including one or more light emitting elements is integrated into the distal end of the elongated body and positioned radially outward of the lens. An integrated processor is disposed within the handle.

Abstract: A fiber optic probe that eliminates extreme tip temperatures by radiating laser energy in a radial, 360° pattern from the surface of an exposed fiber optic tip is disclosed. In an embodiment, a fiber optic core is configured to operatively engage with a source of laser energy at a proximal end of the fiber optic tip, and, at a distal end of the fiber optic tip, includes a plurality of refracting surfaces configured to disperse laser energy in a radial pattern. In one embodiment, the refracting surfaces may be arranged as a plurality of annular prisms defined around the fiber core. In another embodiment, the refracting surfaces may be arranged as a plurality of concave lenses defined in the fiber optic tip. The temperature distribution of the disclosed probes is controlled and uniform, and may be tailored to radiate laser energy in any desired pattern which may be suitable to achieve an intended objective.

Abstract: A fiber optic probe that eliminates extreme tip temperatures by radiating laser energy in a radial, 360° pattern from the surface of an exposed fiber optic tip is disclosed. In an embodiment, a fiber optic core is configured to operatively engage with a source of laser energy at a proximal end of the fiber optic tip, and, at a distal end of the fiber optic tip, includes a plurality of refracting surfaces configured to disperse laser energy in a radial pattern. In one embodiment, the refracting surfaces may be arranged as a plurality of annular prisms defined around the fiber core. In another embodiment, the refracting surfaces may be arranged as a plurality of concave lenses defined in the fiber optic tip. The temperature distribution of the disclosed probes is controlled and uniform, and may be tailored to radiate laser energy in any desired pattern which may be suitable to achieve an intended objective.

Abstract: An endoscope system includes an endoscope, a display device, and a cable interconnecting the endoscope and the display device. The endoscope includes an elongated body extending distally from a handle. An image sensor is disposed within a distal portion of the elongated body, a lens is disposed at a distal end of the elongated body, and a light source including one or more light emitting elements is integrated into the distal end of the elongated body and positioned radially outward of the lens. An integrated processor is disposed within the handle.

Abstract: A system is presented including a first lens for receiving a first image, a second lens for receiving a second image, the first and second lenses being synchronized with each other, and a mirror and prism assembly configured to receive the first and second images. The system further includes a single image sensor configured to receive the first and second images from the mirror and prism assembly, the first image projected onto a first side of the single image sensor and the second image projected onto a second side of the single image sensor. The system may also include at least one processor for separately processing the first image on the first side of the single image sensor and the second image on the second side of the single image sensor to reconstruct a three-dimensional image of an object.

Abstract: A fiber optic probe that eliminates extreme tip temperatures by radiating laser energy in a radial, 360° pattern from the surface of an exposed fiber optic tip is disclosed. In an embodiment, a fiber optic core is configured to operatively engage with a source of laser energy at a proximal end of the fiber optic tip, and, at a distal end of the fiber optic tip, includes a plurality of refracting surfaces configured to disperse laser energy in a radial pattern. In one embodiment, the refracting surfaces may be arranged as a plurality of annular prisms defined around the fiber core. In another embodiment, the refracting surfaces may be arranged as a plurality of concave lenses defined in the fiber optic tip. The temperature distribution of the disclosed probes is controlled and uniform, and may be tailored to radiate laser energy in any desired pattern which may be suitable to achieve an intended objective.

Abstract: An endoscope system includes an endoscope, a display device, and a cable interconnecting the endoscope and the display device. The endoscope includes an elongated body extending distally from a handle. An image sensor is disposed within a distal portion of the elongated body, a lens is disposed at a distal end of the elongated body, and a light source including one or more light emitting elements is integrated into the distal end of the elongated body and positioned radially outward of the lens. An integrated processor is disposed within the handle.