English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 280 Lessons (30h 43m) | 20.49 GB
This deep learning training equips junior data scientists with the expertise needed to implement deep learning solutions for their organization’s specific needs. Building on the principles of machine learning, this course provides an introduction to deep learning, focusing on image data using computer vision (CV), text data using natural language processing (NLP), and time-series data for predictive modeling.
This course will not only teach you how to use TensorFlow for image and text classification, it will also help you gain an understanding of Large Language Models (LLMs).
For anyone with junior data scientists on their team, this data science training can be used to onboard new junior data scientists, curated into individual or team training plans, or as a data science reference resource.
After completing this deep learning training, you’ll know how to describe deep learning methods and techniques well enough to begin implementing deep learning solutions for your organization’s unique needs.
Introduction to Deep Learning: What You Need to Know
This deep learning training has videos that cover topics including:
- Building and training neural networks for image and text classification
- Learning the differences between machine learning and deep learning, and when to use one over the other
- Understanding Convolutional Neural Networks (CNNs) and Natural Language Processing (NLP) techniques
- Evaluating and optimizing deep learning models using pre-trained models from TensorFlow, Google, and Kaggle
Who Should Take Introduction to Deep Learning Training?
This deep learning training is considered associate-level data science training, which means it was designed for data scientists who have a basic understanding of Python programming and machine learning concepts, including supervised and unsupervised learning.
New or aspiring junior data scientists. If you’re a brand new data scientist, this deep learning course can be used to start your career off on the right foot. Gain hands-on experience with deep learning and learn valuable skills you can use to solve complex problems in image and text analysis.
Experienced junior data scientists. Data scientists with a few years of experience have likely encountered deep learning tools or implementations. You may have even struggled through them on your own. This deep learning training will help you bring more value to your organization by augmenting your skills in Convolutional Neural Networks (CNNs) and Natural Language Processing (NLP) for computer vision tasks and text classification analysis.
Table of Contents
Explore Deep Learning Foundational Concepts
1 Introduction
2 What is An Artificial Neuron
3 What is Deep Learning
4 Neural Network Basics
5 Convolutional Neural Networks (CNNs)
6 Natural Language Processing (NLP)
7 Challenge
Set Up a Deep Learning Development Environment
8 Introduction
9 Google Colab
10 Anaconda and Conda
11 Jupyter Notebook
12 PyCharm
13 Visual Studio Code
14 Challenge
15 Solution Video
Explore Computer Vision Foundational Concepts
16 Introduction
17 What is Computer Vision(CV)
18 Explore CV with the fashion MNIST dataset
19 How does SoftMax work
20 Normalizing and Standardization
21 Challenge
22 Solution Video
Examine TensorFlow Convolutional Neural Networks
23 Introduction
24 Load & EDA MNIST Dataset
25 Callbacks Part 1
26 Callbacks Part 2
27 Convolution & Pooling
28 Challenge
29 Solution Video
Build a Computer Vision Model with TensorFlow
30 Introduction
31 Explore the Food 101 dataset on Kaggle
32 Explore the modified ramen sushi dataset
33 Load dataset using ImageDataGenerator
34 Visualize random images with the labels
35 Challenge
36 Solution Video Part 1
37 Solution Video Part 2
Compare Deep and Convolutional Neural Networks
38 Introduction
39 Explore CNNs in a Browser
40 What is a baseline model
41 Deep Neural Networks (DNNs)
42 Convolutional Neural Networks (CNNs)
43 Challenge
44 Solution Video
Ingest Real-world Image Data with TensorFlow
45 Introduction
46 Real-world scenario Teachable Machine Proof of Concept
47 Real-world scenario Teachable Machine Proof of Concept Part 2
48 Real-world scenario Acquire and Upload Images Part 1
49 Real-world scenario Acquire and Upload Images Part 2
50 Challenge
51 Solution Video
Improve CNN Model Performance with TensorFlow
52 Introduction
53 Baseline Model
54 Part 2
55 CNN Model
56 Improvements
57 Challenge
58 Challenge Solution
Visualize to Avoid CNN Overfitting with TensorFlow
59 Introduction
60 Explore Overfitting
61 Load Dataset
62 Challenge 1 Build and Train a Baseline Model from Pseudocode
63 Plot Training Curves
64 Reducing Overfitting
65 Challenge
66 Solution Video
Build a Multi-Class CNN Classifier with TensorFlow
67 Introduction
68 Binary to Multi-Class Classification EDA
69 Build, Compile, and Fit Model
70 Evaluate for Overfitting (plot curves)
71 Adjust HyperparametersData Augmentation
72 Repeat Until Happy with Results
Write an Algorithm to Classify Dog or Cat Images
73 Introduction
74 Kaggle Milestone Challenge Overview
75 Load Dataset with ImageDataGenerator
76 Challenge
77 Solution Video
Explore Transfer Learning with TensorFlow
78 Introduction
79 Explore Dataset and Clone Repo from CBTN GitHub
80 Prepare Train Dataset for Reduction
81 Reduce Train Dataset by 90% and Only Keep 10%
82 CHALLENGE
83 Solution
Leverage Various Callbacks for Transfer Learning
84 Introduction
85 Review Reduced Food 10 Dataset (10%)
86 Custom Callbacks
87 TensorBoard Callbacks
88 Checkpoint Callbacks
89 Early Stopping Callbacks
90 Callback Lists
91 Challenge Introduction
92 Challenge Solution
93 Improved Learning Rate
Reuse Pre-Trained TensorFlow Hub Models of Kaggle
94 Introduction
95 Review Transfer Learning, Feature Extraction, and Fine-Tuning
96 Review Food_10 Dataset
97 Exploring Pre-Trained Models
98 Apply Transfer Learning, Feature Extraction, and Fine-tuning
99 Challenge
100 Solution video
Build TensorFlow Hub Feature Extraction Models
101 Introduction
102 Clone and Create Reduced Food_10 Dataset
103 Apply Data Augmentation
104 Create a custom function to build Keras models simply using URLs
105 Build, compile, and train resnet_model
106 Challenge
107 Solution video
Compare ResNet and EfficientNet Pre-Trained Models
108 Introduction
109 Explore Reduced Food_10 Dataset for Transfer Learning
110 Create re-useable custom functions for rapid testing
111 Import custom functions from CBT Nuggets GitHub repo
112 Double Challenge
113 Build a tensorflowresnet model from scratch
114 Build a tensorflowefficientnet model from scratch
Implement Fine-Tuning with TensorFlow Hub Models
115 Introduction
116 Explore Fine-Tuning
117 Explore Food_10 Dataset
118 Import custom functions with !wget or !clone
119 Create ResNet50 Model
120 Train the Fine-Tuning layers of the model
121 Challenge
122 Solution Video
Fine-Tune TensorFlow Hub Models on Large Datasets
123 Introduction
124 Explore Fine-Tuning
125 Explore Food_10 Dataset in three sizes
126 Explore a new TensorFlow methods
127 Explore Keras Applications Vs TensorFlow Hub
128 Fine-Tune the Top 10 Unfrozen Layers
129 Challenge
130 Challenge Solution Video
131 Update Completed ResNet50 Training & EfficientNetB0 Code
Learn Natural Language Processing with TensorFlow
132 Introduction
133 From Pixels and CNN to Characters with NLP
134 What is ASCII and Why Isn’t Great for Encoding in NLP
135 Using Basic Sequences to Understand Basic Encoding Principles
136 What are Tokens and Tokenizers
137 CHALLENGE
138 Challenge Solution Video
Train Machines to Read with Token Sequences & More
139 Introduction
140 Explore Similarities in Reading for Humans and Machines
141 Apply Token Sequences Aiming for Coherent Outputs
142 Handling Out-of_Vocabulary words with OOV Tokens
143 Adding Uniformity to Sentences with Padding
144 CHALLENGE
145 Challenge Solution
Build an Enhanced Vocabulary with News Headlines
146 Introduction
147 Review Limitations of Song Lyrics Generator Bot
148 Explore News Category Dataset and Preprocessing
149 Apply Sequencing, OOV, and Padding
150 Test User Article Title Input on Our Vocabulary with OOV in Mind
151 CHALLENGE
152 Challenge Solution Video
Apply Sentiment Insights with Text Embeddings
153 Introduction
154 Review Previous NLP Neural Network Classifier
155 Explore TensorFlow Datasets and New Dataset
156 Load IMDB Dataset and Convert to DataFrames
157 Convert Data to Numpy Arrays and review sentences and labels
158 Tokenizer, Sequences, OOV, and Padding and Embeddings
159 CHALLENGE
160 Challenge Solution Video
Analyze Sentiments in Vector Spaces and Embeddings
161 Introduction
162 Use Numpy instead of Pandas to Load Dataset
163 Deep Dive Into Hyperparameters Tuning
164 Deep Dive Into Text Embeddings
165 Plot Loss and Accuracy Curves
166 Analyze Sentiment with Embedding Projector
167 CHALLENGE
168 Solution Video
Apply Real-World Sentiment Analysis with Yelp Data
169 Introduction
170 Review TensorFlow Datasets & Explore Subwords and BSE
171 CHALLENGE
172 Solution Video A
173 , Solution Video B
174 Solution Video C
Transition from Tokenization to Sequence Models
175 Introduction
176 From Token Semantics to Sequential Coherence
177 What is RNN and LSTM
178 The Heart of Sequence Models Sequence Problems
179 TensorFlow Modeling Action Steps
180 Delve Deeper Into RNN and LSTM
181 CHALLENGE
182 Solution Video
Apply TensorFlow NLP to Classify Disaster Tweets
183 Introduction
184 Static Token Vs Dynamic Embeddings
185 NLP with Kaggle’s Disaster Tweets Contest
186 Exploratory Data Analysis with Pandas
187 Data Visualization with Matplotlib and Seaborn
188 CHALLENGE
189 Solution Video
Optimize TensorFlow NLP Disaster Binary Classifier
190 Introduction
191 Review Baseline TensorFlow Binary Disaster Classifier
192 Load and Preprocess Dataset
193 Clean Data Before Improving Model Architecture
194 Clean Data Part 2
195 CHALLENGE
196 Solution Video
Submit Your Tweet Classifier Into a Kaggle Contest
197 Introduction
198 Review Baseline Model Accuracy & Loss
199 Add Random Dataset Shuffle & Hyperparameters
200 Leverage Custom Functions
201 Prepare Competition Output File submission.csv
202 CHALLENGE
203 Solution Video
Transition from SimpleRNN to Bidirectional LSTM
204 Introduction
205 Explore RNNs Models and the Vanishing Gradients Problem
206 Explore Long Short-Term Memory (LSTM) Models
207 Build a Single Layer Bidirectional LSTM Model
208 Build a Multiple Layer Bidirectional LSTM Model
209 Add Convolutions to LSTM Models to Capture Sequences of Words
210 CHALLENGE
211 Solution Video & Code
Compare LSTM, GRU, and Convolutional LSTM Networks
212 Introduction
213 Contrast LSTM, GRU, and Convolutional LSTM
214 Build LSTM model
215 Build GRU model
216 Build Convolutional LSTM model
217 CHALLENGE
218 Solution Video
Move from LSTM to Fine-Tune TensorFlow Hub Models
219 Introduction
220 Review Transfer Learning
221 Searching for Models on TensorFlow Hub
222 CHALLENGE
223 Challenge Solution Video Part 1
224 Challenge Solution Video Part 2
Explore Generative Text Sequence Models in NLP
225 Introduction
226 Explore Generative Text Prediction
227 Initialize and Fit Tokenizer
228 Convert to Numerical Representation of the Corpus
229 Generate and Return N-Gram Sequences
230 Convert Padding Sequences to X and y
231 Explore Tokenized Word Index
232 CHALLENGE
233 Solution Video
Generate Text with Recurrent Neural Networks(RNNs)
234 Introduction
235 Build, Compile and Train Model
236 Plot the Accuracy and Loss Curves
237 Add Bidirectional(LSTM) and Plot Curves
238 Create a Text Prediction Sequence Model
239 CHALLENGE
240 Solution Video
Explore Types of Time Series and Temporal Patterns
241 Introduction
242 What is Univariate Time Series
243 What is Multivariate Time Series
244 Trends
245 Seasonality
246 Autocorrelation
247 Noise
Time Series Forecasting with Deep Neural Networks
248 Introduction
249 Explore Time Series Forecasting Basics
250 Create and Visualize Synthetic Dataset
251 Prepare Data for Training using a windowed_dataset
252 Review Model Architecture
253 CHALLENGE
254 Challenge Solution Video
Explore Time Series with Recurrent Neural Networks
255 Introduction
256 Review DNN Forecasting
257 CHALLENGE 1
258 Complete code challenge
259 Build DNN model
260 Review Recurrent Neural Networks
261 CHALLENGE 2
262 Complete code challenge
263 Build RNN model
Explore Time Series with DNN, RNN, and LSTM
264 Introduction
265 Review DNN Model Architecture
266 CHALLENGE 1 Build DNN Forecasting Model
267 Solution Video
268 Review RNN Model Architecture
269 CHALLENGE 2 Build RNN Forecasting Model
270 Solution Video
271 Review LSTM Model Architecture
272 CHALLENGE 3 Build LSTM Forecasting Model
273 Solution Video
Build a DNN, LSTM, and CNN Sunspot Forecast Model
274 Introduction
275 Review Kaggle Sunspot Dataset & CBT Nuggets GitHub Repo
276 Build Baseline DNN Forecasting Model Part 1
277 Build Baseline DNN Forecasting Model Part 2
278 Review LSTMCNN Model Architecture
279 CHALLENGE Build LSTMCNN Forecasting Model
280 Solution Video
Resolve the captcha to access the links!