As part of this Professional Certificate program, I have learned how to build and train neural networks using TensorFlow, how to improve network performance using convolutions as I train it to identify real-world images. How to teach machines to understand, analyze, and respond to human speech with natural languageprocessing systems, and more!

Learnt how to build time series models in TensorFlow. Implemented the best practices to prepare time series data. Explored how RNNs and 1D ConvNets can be used for prediction. Finally, applied everything I’ve learned throughout the Specialization to build a sunspot prediction model using real-world data!

Learnt to process text, including tokenizing and representing sentences as vectors, so that they can be input to a neural network. Learnt to apply RNNs, GRUs, and LSTMs in TensorFlow. Finally, trained an LSTM on existing text to create original poetry!

Learnt advanced techniques to improve the computer vision models. Explored how to work with real-world images in different shapes and sizes, visualize the journey of an image through convolutions. Explored strategies to prevent overfitting, including augmentation and dropout. Finally, understood transfer learning and how learned features can be extracted from models.

Learnt best practices for using TensorFlow, a popular open-source machine learning framework. Built a basic neural network in TensorFlow. Trained a neural network for a computer vision application. Understood how to use convolutions to improve a neural network.

A three-course Specialization for applying machine learning and deep learning to concrete problems in medicine.

Created a convolutional neural network image classification and segmentation models to make diagnoses of lung and brain disorders.

Developed risk models and survival estimators for heart disease using statistical methods and a random forest predictor to determine patient prognosis

Developed a treatment effect predictor, apply model interpretation techniques and use natural language processing to extract information from radiology reports.

A three course specialization for working on the underlying mathematics, building an intuitive understanding, and relating it to Machine Learning and Data Science via appliying the knowledge to real world problems. For example, using linear algebra in order to calculate the page rank of a small simulated internet, applying multivariate calculus in order to train your own neural network, performing a non-linear least squares regression to fit a model to a data set, and using principal component analysis to determine the features of the MNIST digits data set.

A five course specialization to develop a profound knowledge of the hottest AI algorithms, mastering deep learning from its foundations (neural networks) to its industry applications (Computer Vision, Natural Language Processing, Speech Recognition, etc.).

Understood the major technology trends driving Deep Learning. Built, train and apply fully connected deep neural networks. Implemented efficient (vectorized) neural networks Understood the key parameters in a neural network’s architecture.

Understood industry best-practices for building deep learning applications. Effectively used the common neural network “tricks”, including initialization, L2 and dropout regularization, Batch normalization, gradient checking, Implemented and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence. Understood new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance Implemented a neural network in TensorFlow.

Understood how to diagnose errors in a machine learning system. Able to prioritize the most promising directions for reducing error. Understood complex ML settings, such as mismatched training/test sets, and comparing to and/or surpassing human-level performance. Understood how to apply end-to-end learning, transfer learning, and multi-task learning.

Understood how to build a convolutional neural network, including recent variations such as residual networks. Understood how to apply convolutional networks to visual detection and recognition tasks. Understood how to use neural style transfer to generate art. Able to apply these algorithms to a variety of image, video, and other 2D or 3D data.

Understood how to build and train Recurrent Neural Networks (RNNs), and commonly-used variants such as GRUs and LSTMs. Able to apply sequence models to natural language problems, including text synthesis. Able to apply sequence models to audio applications, including speech recognition and music synthesis.

This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI).