Goto

Collaborating Authors

Deep Learning


Machines that see the world more like humans do

#artificialintelligence

Computer vision systems sometimes make inferences about a scene that fly in the face of common sense. For example, if a robot were processing a scene of a dinner table, it might completely ignore a bowl that is visible to any human observer, estimate that a plate is floating above the table, or misperceive a fork to be penetrating a bowl rather than leaning against it. Move that computer vision system to a self-driving car and the stakes become much higher -- for example, such systems have failed to detect emergency vehicles and pedestrians crossing the street. To overcome these errors, MIT researchers have developed a framework that helps machines see the world more like humans do. Their new artificial intelligence system for analyzing scenes learns to perceive real-world objects from just a few images, and perceives scenes in terms of these learned objects. The researchers built the framework using probabilistic programming, an AI approach that enables the system to cross-check detected objects against input data, to see if the images recorded from a camera are a likely match to any candidate scene.


The Dark Side of Transfer Learning

#artificialintelligence

Transfer learning began as a golden child of image recognition and has quickly become an established pillar of deep learning -- for good reason. Base models allow for a new wave of extraordinarily accessible and effective deep learning applications.



Two-stage Deep Neural Network via Ensemble Learning for Melanoma Classification

#artificialintelligence

Melanoma is a skin disease with a high fatality rate. Early diagnosis of melanoma can effectively increase the survival rate of patients. There are three types of dermoscopy images, malignant melanoma, benign nevis and seborrheic keratosis, so using dermoscopy images to classify melanoma is an indispensable task in diagnosis. However, early melanoma classification works can only use the low-level information of images, so the melanoma cannot be classified efficiently; and the recent deep learning methods mainly depend on a single network, although it can extract high-level features, the poor scale and type of the features limited the results of the classification. Therefore, we need an automatic classification method for melanoma, which can make full use of the rich and deep feature information of images for classification. In this study, we propose an ensemble method that can integrate different types of classification networks for melanoma classification. Specifically, we first use U-net to segment the lesion area of images to generate a lesion mask, thus resize images to focus on the lesion; then, we use five excellent classification models to classify dermoscopy images, and adding squeeze-excitation block (SE block) to models to emphasize the informative features; finally we use our proposed new ensemble network to integrate five different classification results. The experimental results prove the validity of our results. We test our method on the ISIC $2017$ challenge...


Roche announces the release of its newest artificial intelligence based digital pathology algorithms to aid pathologists in evaluation of breast cancer markers, Ki-67, ER and PR

#artificialintelligence

Roche (SIX: RO, ROG; OTCQX: RHHBY) today announced the research use only (RUO) launch of three new automated digital pathology algorithms, uPath Ki-67 (30-9), uPath ER (SP1) and uPath PR (1E2) image analysis for breast cancer, which are important biomarkers for breast cancer patients. Breast cancer is the second most common cancer in the world with an estimated 2.3 million new cases in 2020¹ and is the most common cancer in women globally¹,². These new algorithms complete the Roche digital pathology breast panel of image analysis algorithms. This includes a whole slide analysis workflow with automated pre-computing of the slide image prior to pathologist assessment, and a clear visual overlay highlighting tumour cells with and without nuclear staining. Intended for use with Roche's high medical value assays and slides stained on a BenchMark ULTRA instrument using ultraView DAB detection kit, the uPath Ki-67 (30-9) image analysis, uPath ER (SP1) image analysis and uPath PR (1E2) image analysis algorithms are ready-to-use and integrated within Roche's uPath enterprise software and NAVIFY Digital Pathology, the cloud version of uPath.


Raster Vision: A Geospatial Deep Learning Framework

#artificialintelligence

A satellite image is more than its pixels -- it is also its location. Typically encoded as a GeoTiff, such an image will also have georeferencing metadata -- such as coordinates, a coordinate system, and a projection transform -- that defines a mapping from pixel-based coordinates (ie. The same holds true for any annotations we might create for such an image -- these might take the form of GeoJSON files with vector annotations (eg. With the right tools, we can extract from these files a correctly transformed raster image and a corresponding label that we can happily feed into our computer vision models; but ultimately, to be useful in the real world, any insights gained from these models must also be mapped back to geographical locations. What use is detecting a wildfire if we don't know where it is?


Using Datawig, an AWS Deep Learning Library for Missing Value Imputation - KDnuggets

#artificialintelligence

While training a Machine Learning model the quality of the model is directly proportional to the quality of data. However, in some cases, there are a lot of missing values in the dataset affecting the quality of prediction in the long run. Several methods can be used to fill the missing values and Datawig is one of the most efficient ones. Datawig is a Deep Learning library developed by AWS Labs and is primarily used for "Missing Value Imputation". The library uses "mxnet" as a backend to train the model and generate the predictions.


Post Graduate Program on Applied Data Science with Deep Learning and Specialisation(TEKS-RISE) - Teksands

#artificialintelligence

If it is your goal is to become a Data Scientist, you have to first understand what it takes to become one, the skills and competencies that you should learn. Data Science is an amazingly interesting field, full of interesting concepts and power to create magic from Data. Comprehensive knowledge on Deep Learning, ML-Ops and AI/ML Product Development are critical knowledge areas for any Data Scientist/Data Engineer/Machine-Learning Professional. This course places a lot of focus into these areas so that there is no learning gap when you start on a Data Science/Machine Learning role. The curriculum prepares you to be a leader in this field through mastery of core data science concepts like Statistical Analysis of Data, Exploratory Data Analysis Techniques using Python, powerful Visualizations, Machine Learning, Deep Learning and Model Deployment in Production.


Fundamentals in Neural Networks

#artificialintelligence

Beginner level audience that intends to obtain in-depth overview of Artificial Intelligence, Deep Learning, and three major types neural networks: Artificial Neural Networks, Convolutional Neural Networks, and Recurrent Neural Networks. Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised. Deep-learning architectures such as deep neural networks, deep belief networks, deep reinforcement learning, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, speech recognition, natural language processing, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance. This course covers the following three sections: (1) Neural Networks, (2) Convolutional Neural Networks, and (3) Recurrent Neural Networks.


Why Artificial Intelligence is Critical for Innovation and Growth

#artificialintelligence

AI is making its presence felt everywhere in the connected world whether via data-driven deep learning technologies, smart robots, or autonomous vehicles. Industries ranging from manufacturing, retail, to healthcare and aerospace have all witnessed some remarkable examples of how AI technology is changing the way they do business in recent times. The impact of AI on an organization's ability to harness data and unlock new opportunities is huge. The transformative powers of AI-enabled solutions in enhancing the capabilities of business analytics and business intelligence have helped them achieve a prominent place in the Gartner Hype Cycle for Emerging Technologies. The sudden surge in the volume and complexity of data is driving the commercial adoption of AI across many industries.