tering using both implicit & explicit feedback
Day 2
8:00 AM - 8:50AM Practical Machine Learning In-Depth: Feature Engineering,
>From Regression to Classification, 5 Tribes of Machine Learning: Symbolists
with Inverse Deduction of Symbolic Logic, Connectionists with Backpropagation
of Neural Networks, Evolutionaries with Genetic Programming, Bayesians with
Probabilistic Inference in Statistics, Analogizers with Support Vector
Machines; Supervised Learning (Classification/Regression), Unsupervised
Learning (Clustering), Semi-Supervised Learning; Data Ingestion & Its
Challenges, Data Cleansing/Prep-processing; Training Set/Testing Set
Partitioning; Feature Engineering (Feature
Extraction/Selection/Construction/Learning, Dimension Reduction); Model
Building/Evaluation/Deployment|Serving/Scaling|Reduction/Optimization with
Prediction Feedbacks
9:00 AM - 9:50AM Practical Deep-Learning-based AI In-Depth: Weak/Special AI vs
Strong/General AI; Key Components of AI: Knowledge Representation, Deduction,
Reasoning, NLP, Planning, Learning,Perception, Sensing & Actuation, Goals &
Problem Solving, Consciousness & Creativity; Rectangle of Deep Learning,
Shallow Learning, Supervised Learning, and Unsupervised Learning; Basic
Multi-layer Architecture of Deep Forward/Convolutional Neural
Networks(FNN/CNN)/Deep Recurrent Neural Networks(RNN)/Long short-term
memory(LSTM): Input/Hidden/Output Layers, Weights, Biases, Activation Function,
Feedback Loops, Backpropagation from Automatic Differentiation and Stochastic
Gradient Descent (SGD); Convex/Non-Convex Optimization; Ways of Training Deep
Neural Networks: Data/Model Parallelism, Synchronous/Asynchronous Training,
Variants of SGD, Gradient Vanishing/Explotion, Loss Function
Minimization/Optimization with Dropout/Regulariztion & Batch Normalization &
Learning Rate & Training Steps, and Unsupervised Pre-training (Autoencoder
etc.); Deep Learning Applications - What's Fit and What's Not?: Deep
Structures, Unusual RNN, Huge Models
10:00 AM - 10:50PM Embracing Paradigm Shifting from Algorithm-based Rigid
Computing to Model-based Big Data Cloud IoT-powered Deep Learning AI for
Real-Life Problem Solving: What, Why and How? - Problem Formulation, Data
Gathering, Algorithmic & Neural Network Architecture Selection, Hyperparameter
Turning, Deep Learning, Cross Validation, and Model Serving
11:00 AM - 11:50AM Tensorflow In-Depth: The Origin, Fundamental Concepts
(Tensors/Data Flow Graph & More), Historical Development & Theoretical
Foundation; Two Major Deep Learning Models and Their TensorFlow Implementation:
Convolutional Neural Network (CNN), Recurrent Neural Network (RNN);
GPU/Tensorflow vs. CPU/NumPy; TensorFlow vs Other Open Source Deep Learning
Packages: Torch, Caffe, MXNet, Theano: Programming vs. Configuration; Tackling
Deep Learning Blackbox Puzzle with TensorBoard
12:00 PM - 1:00PM Lunch Break (Lunch included, Veggie option available)
1:00PM - 5PM Hands-on II: Architect, Design & Develop (Modeling/Training ->
Inferencing/Testing) Your Own Chosen AI Application Using Python in Your Own
Scalable AI Big Data Google/AWS Cloud|CoreOS Container Cluster (Hadoop, Spark,
Kafka, HBase, HIVE, Tensorflow)
Who Should Attend:
CEO, SVP/VP, C-Level, Director, Global Head, Manager, Decision-makers, Business
Executives, Analysts, Project managers, Analytics managers, Data Scientist,
Statistian, Sales, Marketing, human resources, Engineers, Developers,
Architects, Networking specialists, Students, Professional Services, Data
Analyst, BI Developer/Architect, QA, Performance Engineers, Data Warehouse
Professional, Sales, Pre Sales, Technical Marketing, PM, Teaching Staff,
Delivery Manager and other line-of-business executives
Statisticians, Big Data Engineer, Data Scientists, Business Intelligence
professionals, Teaching Staffs, Delivery Managers, Product Managers, Cloud
Operaters, Devops, System admins, Business Analysts, Financial Analysts,
Solution Architects, Pre-sales, Sales, Post-Sales, Marketers, Project Managers,
and Big Data Cloud AI Enthusiasts.
Hands-on Requirements:
1) Each student should bring their own 64bit Linux-based or Windows with Putty
installed laptop (no VM required as we are using cloud) with Minimum 8GB RAM
and Free 0.5TB hard disk with administrative/root privileges and wireless
connectivity.
2) Own wireless connection (hot spot)
3) Google/AWS Cloud account ready|Pre-installed Docker/CoreOS in your laptop
4) Reasonable Bash or Python
Forbes Z
CLO
Deep Learning Cloud/Container Boot Camp: Build & Operate End-to-End Data
Pipeline & Data Lake with TensorFlow, Spark & Hadoop in API (Python)/CLI(Bash)
- www.tinyurl.com/AIBootCamp ( RSVP for 3/11-12)
- www.tinyurl.com/AIBootCamp2 (RSVP for 4/15-16)
- www.tinyurl.com/AIBootCampX (RSVP for Anytime Anywhere with Group of 30)
- www.hwswworld.com/aibootcampoverview3.pdf - 60-page Boot Camp Overview Slides
@ClouDatAI for Latest Boot Camp Update - 1M Tweets/Yr., 2.6M Tweets so far
Cloudata Inc - DAOing Your AI Big Data Cloud IoT!
