Learn SQL Fundamentals This Weekend! Enroll Now

Accredited Professional Development Data Science Course

Deep Learning with TensorFlow

Offered Live Online & In Person

Deep learning has become standard in the tech industry, achieving state-of-the-art results in computer vision, natural language processing, and artificial intelligence. This course teaches the core concepts of deep learning using TensorFlow, Google’s open-source computation graph library.

Who the course is designed for:

Those who want to rapidly gain an overview of the major concepts and topics of deep learning from a theoretical and applied perspective. In order to make advances in this field or even use pre-trained models, strong theoretical knowledge of deep learning concepts is critical. However, this theoretical knowledge must be complemented with practical implementation skills.  The goal of this course is to convey both the theory and practice of deep learning in an accelerated format. Thus, the goal of the course is to teach not only the how but also the why of deep learning.

The course will focus on developing an understanding of the core ideas of deep representational learning including units in feedforward neural networks, hyperparameter tuning, convolutional neural networks, recurrent neural networks and other topics as time allows for. The basic concepts and APIs of TensorFlow (Google’s Deep Learning Framework) will be taught in conjunction with the theoretical concepts in order to illustrate how the core principles of deep learning can be applied in a computational environment. 


  • Exposure to and understanding of the major topics and concepts of deep learning, which may serve as a springboard for further study and application in professional or research settings
  • Practical hands-on experience in developing TensorFlow programs and an overview of the key principles of the TensorFlow programming environment and APIs
  • Exposure to cutting-edge research papers in the deep learning field and examples of how ideas from these papers can be tested and evaluated in TensorFlow
Have questions? Get answers to frequently asked questions. FAQs

What you'll receive upon completion:

  • Certificate of completion
  • 3.3 Continuing Education Units

Dates & Instructors

Check back soon for our next scheduled course.


The class is designed for people who have had little or no exposure to deep learning and deep neural networks and is designed to be an accelerated survey of the field. The course should be highly accessible for people with a broad range of backgrounds.  No data science background is required. The course should be highly accessible for students with or without a degree in a technical discipline.

However, deep learning is not an entry-level subject. Ideally, students should have some familiarity with differential univariate and multivariate calculus, basic linear algebra and probability and statistics. We recognize that some or all of the mathematics may be rusty or long-forgotten. To this end the course will provide a math review covering the important mathematical tools relevant to support the topics covered. Students should also have basic skills in Python programming and be comfortable installing software frameworks within their chosen computing environment.

Considering our immersive data science bootcamp?

Professional development alumni can apply the amount of tuition paid for one part-time course towards enrollment in an upcoming bootcamp upon admittance.

Course Structure & Syllabus

Unit 1
Linear Algebra, Calculus, TensorFlow, and Machine Learning Fundamentals

This course will start with a review of linear algebra and calculus. While you won’t need all of the theoretical knowledge from those subjects, certain practical techniques are necessary, including:

  • Single variable derivatives
  • Summations (and derivatives of summations)
  • Matrix multiplication
  • Matrix manipulation (transpose, inverse)

Get acquainted with the TensorFlow framework and develop an intuition for techniques used throughout machine learning.

  • Installing TensorFlow
  • TensorFlow core API
  • Introduction to TensorBoard
  • Linear, logistic regression
Unit 2
Neural Network Basics

Once familiarity with basic machine learning concepts is established, introduce the feedforward neural network, which lays the foundation for the rest of the models in the class.

  • Neural network structure
  • Neurons, activation functions (sigmoid, tanh, ReLU)
  • Forward propagation and backpropagation
  • Dropout, softmax, cross-entropy
  • Gradient descent
Unit 3
Convolutional Neural Networks

Using pixels as independent inputs has several weaknesses. Is there a better way? Yes! Convolutional layers are inspired from traditional image processing techniques and are currently used in all manner of state of the art convolutional neural networks, or CNNs.

  • Convolutions, pooling
  • AlexNet, ResNet, Inception, and beyond
  • Transfer learning (for fun and profit!)
  • Object detection
Unit 4
Recurrent Neural Networks

Sometimes your inputs come in various lengths such as text (each sentence could be of different length), or are naturally sequential (such as time series). Recurrent neural networks (RNNs) are designed to handle data that comes in different lengths and have become incredibly popular for various natural language processing tasks.

  • RNN basics
  • Long short term memory (LSTM)
  • Sentence classification
  • Text generation
Unit 5
Deploying TensorFlow Models

TensorFlow includes functionality to help developers easily put their models up in a deployment setting, which is one of the more attractive features of the software. With this, students should be able to take their trained models and get them ready to be used out in the wild.

  • Rudimentary TensorFlow deployment in pure Python
  • Setting up a basic TensorFlow Serving server (with some C++)
  • Accessing your model server remotely

Live Online Interactive Learning

Learn from world-class data science practitioners.

Our Live Online instructors bring deep industry experience from a broad range of industries and companies including Viacom, Spotify, and Capital One Labs. You’ll have an Instructor and Assistant Instructor to support you throughout your learning process.

Interact with instructors and classmates in real-time.

This course is truly live, which means you can interact with the instructors and your fellow students in real-time. Stay engaged by asking questions and participating in polls and conversations, and join your course Slack channel for additional support, communication, and collaboration.

Learn online without sacrificing the value of live instruction.

The world is your classroom. Log in from wherever you are and gain access to live, interactive data science instruction that will push your career further in the right direction. In case you have to miss a class, you can access all recordings 24/7 to stay caught up and refer back.

Earn CEUs for accredited courses.

Not only will you walk away with new data science skills and knowledge, you’ll also earn up to 3.3 Continuing Education Units (CEUs). Our courses are accredited by ACCET, who requires we maintain high standards in areas such as quality of instruction and positive student feedback.

Register for an on-demand sample class

Our 1-hour on-demand online sample class is a great way to preview what the Live Online experience is like.

Jon Lederman, instructor of the Live Online Deep Learning with TensorFlow course, will cover a couple topics in the on-demand sample class:

  1. Demystifying Deep Neural Networks (DNNs). What areDeep Neural Networks and why are they useful?
  2. Implementation of Deep Neural Networks in TensorFlow

* By submitting this form you allow Metis to send you awesome updates on events, content, courses & more!


Have more questions? No problem. Schedule a chat with admissions