Atnaujinkite slapukų nuostatas

Deep Learning for NLP and Speech Recognition 2019 ed. [Kietas viršelis]

4.67/5 (6 ratings by Goodreads)
, ,
  • Formatas: Hardback, 621 pages, aukštis x plotis: 254x178 mm, weight: 1417 g, 300 Illustrations, color; 13 Illustrations, black and white; XXVIII, 621 p. 313 illus., 300 illus. in color., 1 Hardback
  • Išleidimo metai: 24-Jun-2019
  • Leidėjas: Springer Nature Switzerland AG
  • ISBN-10: 3030145956
  • ISBN-13: 9783030145958
Kitos knygos pagal šią temą:
Deep Learning for NLP and Speech Recognition 2019 ed.Didesnis paveikslėlis
  • Formatas: Hardback, 621 pages, aukštis x plotis: 254x178 mm, weight: 1417 g, 300 Illustrations, color; 13 Illustrations, black and white; XXVIII, 621 p. 313 illus., 300 illus. in color., 1 Hardback
  • Išleidimo metai: 24-Jun-2019
  • Leidėjas: Springer Nature Switzerland AG
  • ISBN-10: 3030145956
  • ISBN-13: 9783030145958
Kitos knygos pagal šią temą:
Pastovi nuoroda: https://www.kriso.lt/db/9783030145958.html
This textbook explains Deep Learning Architecture, with applications to various NLP Tasks, including Document Classification, Machine Translation, Language Modeling, and Speech Recognition. With the widespread adoption of deep learning, natural language processing (NLP),and speech applications in many areas (including Finance, Healthcare, and Government) there is a growing need for one comprehensive resource that maps deep learning techniques to NLP and speech and provides insights  into  using  the  tools  and  libraries  for  real-world  applications. Deep Learning for NLP and Speech Recognition explains recent deep learning methods applicable to NLP and speech, provides state-of-the-art approaches, and offers real-world case studies with code to provide hands-on experience.  

Many books focus on deep learning theory or deep learning for NLP-specific tasks while others are cookbooks for tools and libraries, but the constant flux of new algorithms, tools, frameworks, and libraries in a rapidly evolving landscape means that there are few available texts that offer the material in this book. 

The book is organized into three parts, aligning to different groups of readers and their expertise. The three parts are:

      Machine Learning, NLP, and Speech Introduction

The first part has three chapters that introduce readers to the fields of  NLP, speech recognition,  deep learning and machine learning with basic theory and hands-on case studies using Python-based tools and libraries.

      Deep Learning Basics

The five chapters in the second part introduce deep learning and various topics that are crucial for speech and text processing, including word embeddings, convolutional neural networks, recurrent neural networks and speech recognition basics. Theory, practical tips, state-of-the-art methods, experimentations and analysis in using the methods discussed in theory on real-world tasks.

      Advanced Deep Learning Techniques for Text and Speech

The third part has five chapters that discuss the latest and cutting-edge research in the areas of deep learning that intersect with NLP and speech. Topics including attention mechanisms, memory augmented networks, transfer learning, multi-task learning, domain adaptation, reinforcement learning, and end-to-end deep learning for speech recognition are covered using case studies. 
Part I Machine Learning, NLP, and Speech Introduction
1 Introduction
3(36)
1.1 Machine Learning
5(2)
1.1.1 Supervised Learning
5(1)
1.1.2 Unsupervised Learning
6(1)
1.1.3 Semi-Supervised Learning and Active Learning
7(1)
1.1.4 Transfer Learning and Multitask Learning
7(1)
1.1.5 Reinforcement Learning
7(1)
1.2 History
7(11)
1.2.1 Deep Learning: A Brief History
8(3)
1.2.2 Natural Language Processing: A Brief History
11(4)
1.2.3 Automatic Speech Recognition: A Brief History
15(3)
1.3 Tools, Libraries, Datasets, and Resources for the Practitioners
18(7)
1.3.1 Deep Learning
18(1)
1.3.2 Natural Language Processing
19(1)
1.3.3 Speech Recognition
20(1)
1.3.4 Books
21(1)
1.3.5 Online Courses and Resources
21(1)
1.3.6 Datasets
22(3)
1.4 Case Studies and Implementation Details
25(2)
References
27(12)
2 Basics of Machine Learning
39(48)
2.1 Introduction
39(1)
2.2 Supervised Learning: Framework and Formal Definitions
40(2)
2.2.1 Input Space and Samples
40(1)
2.2.2 Target Function and Labels
41(1)
2.2.3 Training and Prediction
41(1)
2.3 The Learning Process
42(1)
2.4 Machine Learning Theory
43(12)
2.4.1 Generalization-Approximation Trade-Off via the Vapnik-Chervonenkis Analysis
43(3)
2.4.2 Generalization-Approximation Trade-off via the Bias-Variance Analysis
46(1)
2.4.3 Model Performance and Evaluation Metrics
47(3)
2.4.4 Model Validation
50(3)
2.4.5 Model Estimation and Comparisons
53(1)
2.4.6 Practical Tips for Machine Learning
54(1)
2.5 Linear Algorithms
55(12)
2.5.1 Linear Regression
55(3)
2.5.2 Perception
58(1)
2.5.3 Regularization
59(2)
2.5.4 Logistic Regression
61(3)
2.5.5 Generative Classifiers
64(2)
2.5.6 Practical Tips for Linear Algorithms
66(1)
2.6 Non-linear Algorithms
67(2)
2.6.1 Support Vector Machines
68(1)
2.6.2 Other Non-linear Algorithms
69(1)
2.7 Feature Transformation, Selection, and Dimensionality Reduction
69(3)
2.7.1 Feature Transformation
70(1)
2.7.2 Feature Selection and Reduction
71(1)
2.8 Sequence Data and Modeling
72(6)
2.8.1 Discrete Time Markov Chains
72(1)
2.8.2 Discriminative Approach: Hidden Markov Models
73(2)
2.8.3 Generative Approach: Conditional Random Fields
75(3)
2.9 Case Study
78(7)
2.9.1 Software Tools and Libraries
78(1)
2.9.2 Exploratory Data Analysis (EDA)
78(1)
2.9.3 Model Training and Hyperparameter Search
79(4)
2.9.4 Final Training and Testing Models
83(2)
2.9.5 Exercises for Readers and Practitioners
85(1)
References
85(2)
3 Text and Speech Basics
87(54)
3.1 Introduction
87(3)
3.1.1 Computational Linguistics
87(1)
3.1.2 Natural Language
88(1)
3.1.3 Model of Language
89(1)
3.2 Morphological Analysis
90(2)
3.2.1 Stemming
91(1)
3.2.2 Lemmatization
92(1)
3.3 Lexical Representations
92(4)
3.3.1 Tokens
92(1)
3.3.2 Stop Words
93(1)
3.3.3 N-Grams
93(1)
3.3.4 Documents
94(2)
3.4 Syntactic Representations
96(5)
3.4.1 Part-of-Speech
97(2)
3.4.2 Dependency Parsing
99(2)
3.5 Semantic Representations
101(4)
3.5.1 Named Entity Recognition
102(1)
3.5.2 Relation Extraction
103(1)
3.5.3 Event Extraction
104(1)
3.5.4 Semantic Role Labeling
104(1)
3.6 Discourse Representations
105(1)
3.6.1 Cohesion
105(1)
3.6.2 Coherence
105(1)
3.6.3 Anaphora/Cataphora
105(1)
3.6.4 Local and Global Coreference
106(1)
3.7 Language Models
106(3)
3.7.1 N-Gram Model
107(1)
3.7.2 Laplace Smoothing
107(1)
3.7.3 Out-of-Vocabulary
108(1)
3.7.4 Perplexity
108(1)
3.8 Text Classification
109(4)
3.8.1 Machine Learning Approach
109(1)
3.8.2 Sentiment Analysis
110(2)
3.8.3 Entailment
112(1)
3.9 Text Clustering
113(2)
3.9.1 Lexical Chains
114(1)
3.9.2 Topic Modeling
114(1)
3.10 Machine Translation
115(1)
3.10.1 Dictionary Based
115(1)
3.10.2 Statistical Translation
116(1)
3.11 Question Answering
116(3)
3.11.1 Information Retrieval Based
117(1)
3.11.2 Knowledge-Based QA
118(1)
3.11.3 Automated Reasoning
118(1)
3.12 Automatic Summarization
119(1)
3.12.1 Extraction Based
119(1)
3.12.2 Abstraction Based
120(1)
3.13 Automated Speech Recognition
120(2)
3.13.1 Acoustic Model
120(2)
3.14 Case Study
122(12)
3.14.1 Software Tools and Libraries
123(1)
3.14.2 EDA
123(3)
3.14.3 Text Clustering
126(3)
3.14.4 Topic Modeling
129(2)
3.14.5 Text Classification
131(2)
3.14.6 Exercises for Readers and Practitioners
133(1)
References
134(7)
Part II Deep Learning Basics
4 Basics of Deep Learning
141(62)
4.1 Introduction
141(2)
4.2 Perceptron Algorithm Explained
143(3)
4.2.1 Bias
143(3)
4.2.2 Linear and Non-linear Separability
146(1)
4.3 Multilayer Perceptron (Neural Networks)
146(8)
4.3.1 Training an MLP
147(1)
4.3.2 Forward Propagation
148(1)
4.3.3 Error Computation
149(1)
4.3.4 Backpropagation
150(2)
4.3.5 Parameter Update
152(1)
4.3.6 Universal Approximation Theorem
153(1)
4.4 Deep Learning
154(11)
4.4.1 Activation Functions
155(6)
4.4.2 Loss Functions
161(1)
4.4.3 Optimization Methods
162(3)
4.5 Model Training
165(10)
4.5.1 Early Stopping
165(1)
4.5.2 Vanishing/Exploding Gradients
166(1)
4.5.3 Full-Batch and Mini-Batch Gradient Decent
167(1)
4.5.4 Regularization
167(4)
4.5.5 Hyperparameter Selection
171(1)
4.5.6 Data Availability and Quality
172(2)
4.5.7 Discussion
174(1)
4.6 Unsupervised Deep Learning
175(8)
4.6.1 Energy-Based Models
175(1)
4.6.2 Restricted Boltzmann Machines
176(2)
4.6.3 Deep Belief Networks
178(1)
4.6.4 Autoencoders
178(4)
4.6.5 Sparse Coding
182(1)
4.6.6 Generative Adversarial Networks
182(1)
4.7 Framework Considerations
183(4)
4.7.1 Layer Abstraction
184(1)
4.7.2 Computational Graphs
185(1)
4.7.3 Reverse-Mode Automatic Differentiation
186(1)
4.7.4 Static Computational Graphs
186(1)
4.7.5 Dynamic Computational Graphs
187(1)
4.8 Case Study
187(12)
4.8.1 Software Tools and Libraries
187(1)
4.8.2 Exploratory Data Analysis (EDA)
188(1)
4.8.3 Supervised Learning
189(4)
4.8.4 Unsupervised Learning
193(3)
4.8.5 Classifying with Unsupervised Features
196(2)
4.8.6 Results
198(1)
4.8.7 Exercises for Readers and Practitioners
198(1)
References
199(4)
5 Distributed Representations
203(60)
5.1 Introduction
203(1)
5.2 Distributional Semantics
203(19)
5.2.1 Vector Space Model
203(2)
5.2.2 Word Representations
205(1)
5.2.3 Neural Language Models
206(2)
5.2.4 word2vec
208(11)
5.2.5 GloVe
219(2)
5.2.6 Spectral Word Embeddings
221(1)
5.2.7 Multilingual Word Embeddings
222(1)
5.3 Limitations of Word Embeddings
222(5)
5.3.1 Out of Vocabulary
222(1)
5.3.2 Antonymy
223(1)
5.3.3 Polysemy
224(3)
5.3.4 Biased Embeddings
227(1)
5.3.5 Other Limitations
227(1)
5.4 Beyond Word Embeddings
227(11)
5.4.1 Subword Embeddings
228(1)
5.4.2 Word Vector Quantization
228(2)
5.4.3 Sentence Embeddings
230(2)
5.4.4 Concept Embeddings
232(1)
5.4.5 Retrofitting with Semantic Lexicons
233(1)
5.4.6 Gaussian Embeddings
234(2)
5.4.7 Hyperbolic Embeddings
236(2)
5.5 Applications
238(5)
5.5.1 Classification
239(1)
5.5.2 Document Clustering
239(1)
5.5.3 Language Modeling
240(1)
5.5.4 Text Anomaly Detection
241(1)
5.5.5 Contextualized Embeddings
242(1)
5.6 Case Study
243(16)
5.6.1 Software Tools and Libraries
243(1)
5.6.2 Exploratory Data Analysis
243(1)
5.6.3 Learning Word Embeddings
244(12)
5.6.4 Document Clustering
256(1)
5.6.5 Word Sense Disambiguation
257(2)
5.6.6 Exercises for Readers and Practitioners
259(1)
References
259(4)
6 Convolutional Neural Networks
263(52)
6.1 Introduction
263(1)
6.2 Basic Building Blocks of CNN
264(9)
6.2.1 Convolution and Correlation in Linear Time-Invariant Systems
264(1)
6.2.2 Local Connectivity or Sparse Interactions
265(1)
6.2.3 Parameter Sharing
266(1)
6.2.4 Spatial Arrangement
266(4)
6.2.5 Detector Using Nonlinearity
270(1)
6.2.6 Pooling and Subsampling
271(2)
6.3 Forward and Backpropagation in CNN
273(3)
6.3.1 Gradient with Respect to Weights
274(1)
6.3.2 Gradient with Respect to the Inputs
275(1)
6.3.3 Max Pooling Layer
276(1)
6.4 Text Inputs and CNNs
276(5)
6.4.1 Word Embeddings and CNN
277(3)
6.4.2 Character-Based Representation and CNN
280(1)
6.5 Classic CNN Architectures
281(4)
6.5.1 LeNet-5
282(1)
6.5.2 AlexNet
283(2)
6.5.3 VGG-16
285(1)
6.6 Modern CNN Architectures
285(7)
6.6.1 Stacked or Hierarchical CNN
286(1)
6.6.2 Dilated CNN
287(1)
6.6.3 Inception Networks
288(1)
6.6.4 Other CNN Structures
289(3)
6.7 Applications of CNN in NLP
292(5)
6.7.1 Text Classification and Categorization
293(1)
6.7.2 Text Clustering and Topic Mining
294(1)
6.7.3 Syntactic Parsing
294(1)
6.7.4 Information Extraction
294(1)
6.7.5 Machine Translation
295(1)
6.7.6 Summarizations
296(1)
6.7.7 Question and Answers
296(1)
6.8 Fast Algorithms for Convolutions
297(3)
6.8.1 Convolution Theorem and Fast Fourier Transform
297(1)
6.8.2 Fast Filtering Algorithm
297(3)
6.9 Case Study
300(10)
6.9.1 Software Tools and Libraries
300(1)
6.9.2 Exploratory Data Analysis
301(1)
6.9.3 Data Preprocessing and Data Splits
301(2)
6.9.4 CNN Model Experiments
303(4)
6.9.5 Understanding and Improving the Models
307(2)
6.9.6 Exercises for Readers and Practitioners
309(1)
6.10 Discussion
310(1)
References
310(5)
7 Recurrent Neural Networks
315(54)
7.1 Introduction
315(1)
7.2 Basic Building Blocks of RNNs
316(2)
7.2.1 Recurrence and Memory
316(1)
7.2.2 PyTorch Example
317(1)
7.3 RNNs and Properties
318(9)
7.3.1 Forward and Backpropagation in RNNs
318(5)
7.3.2 Vanishing Gradient Problem and Regularization
323(4)
7.4 Deep RNN Architectures
327(6)
7.4.1 Deep RNNs
327(1)
7.4.2 Residual LSTM
328(1)
7.4.3 Recurrent Highway Networks
329(1)
7.4.4 Bidirectional RNNs
329(2)
7.4.5 SRU and Quasi-RNN
331(1)
7.4.6 Recursive Neural Networks
331(2)
7.5 Extensions of Recurrent Networks
333(6)
7.5.1 Sequence-to-Sequence
334(1)
7.5.2 Attention
335(1)
7.5.3 Pointer Networks
336(1)
7.5.4 Transformer Networks
337(2)
7.6 Applications of RNNs in NLP
339(9)
7.6.1 Text Classification
339(1)
7.6.2 Part-of-Speech Tagging and Named Entity Recognition
340(1)
7.6.3 Dependency Parsing
340(1)
7.6.4 Topic Modeling and Summarization
340(1)
7.6.5 Question Answering
341(1)
7.6.6 Multi-Modal
341(1)
7.6.7 Language Models
341(2)
7.6.8 Neural Machine Translation
343(3)
7.6.9 Prediction/Sampling Output
346(2)
7.7 Case Study
348(16)
7.7.1 Software Tools and Libraries
349(1)
7.7.2 Exploratory Data Analysis
349(6)
7.7.3 Model Training
355(7)
7.7.4 Results
362(1)
7.7.5 Exercises for Readers and Practitioners
363(1)
7.8 Discussion
364(1)
7.8.1 Memorization or Generalization
364(1)
7.8.2 Future of RNNs
365(1)
References
365(4)
8 Automatic Speech Recognition
369(38)
8.1 Introduction
369(1)
8.2 Acoustic Features
370(7)
8.2.1 Speech Production
370(1)
8.2.2 Raw Waveform
371(1)
8.2.3 MFCC
372(4)
8.2.4 Other Feature Types
376(1)
8.3 Phones
377(2)
8.4 Statistical Speech Recognition
379(8)
8.4.1 Acoustic Model: P(X\W)
381(4)
8.4.2 LanguageModel: P(W)
385(1)
8.4.3 HMM Decoding
386(1)
8.5 Error Metrics
387(1)
8.6 DNN/HMM Hybrid Model
388(3)
8.7 Case Study
391(12)
8.7.1 Dataset: Common Voice
392(1)
8.7.2 Software Tools and Libraries
392(1)
8.7.3 Sphinx
392(4)
8.7.4 Kaldi
396(5)
8.7.5 Results
401(1)
8.7.6 Exercises for Readers and Practitioners
402(1)
References
403(4)
Part III Advanced Deep Learning Techniques for Text and Speech
9 Attention and Memory Augmented Networks
407(56)
9.1 Introduction
407(1)
9.2 Attention Mechanism
408(11)
9.2.1 The Need for Attention Mechanism
409(1)
9.2.2 Soft Attention
410(1)
9.2.3 Scores-Based Attention
411(1)
9.2.4 Soft vs. Hard Attention
412(1)
9.2.5 Local vs. Global Attention
412(1)
9.2.6 Self-Attention
413(1)
9.2.7 Key-Value Attention
414(1)
9.2.8 Multi-Head Self-Attention
415(1)
9.2.9 Hierarchical Attention
416(2)
9.2.10 Applications of Attention Mechanism in Text and Speech
418(1)
9.3 Memory Augmented Networks
419(21)
9.3.1 Memory Networks
419(3)
9.3.2 End-to-End Memory Networks
422(2)
9.3.3 Neural Turing Machines
424(4)
9.3.4 Differentiable Neural Computer
428(3)
9.3.5 Dynamic Memory Networks
431(3)
9.3.6 Neural Stack, Queues, and Deques
434(3)
9.3.7 Recurrent Entity Networks
437(3)
9.3.8 Applications of Memory Augmented Networks in Text and Speech
440(1)
9.4 Case Study
440(20)
9.4.1 Attention-Based NMT
440(1)
9.4.2 Exploratory Data Analysis
441(9)
9.4.3 Question and Answering
450(5)
9.4.4 Dynamic Memory Network
455(4)
9.4.5 Exercises for Readers and Practitioners
459(1)
References
460(3)
10 Transfer Learning: Scenarios, Self-Taught Learning, and Multitask Learning
463(32)
10.1 Introduction
463(1)
10.2 Transfer Learning: Definition, Scenarios, and Categorization
464(3)
10.2.1 Definition
465(1)
10.2.2 Transfer Learning Scenarios
466(1)
10.2.3 Transfer Learning Categories
466(1)
10.3 Self-Taught Learning
467(4)
10.3.1 Techniques
468(1)
10.3.2 Theory
469(1)
10.3.3 Applications in NLP
470(1)
10.3.4 Applications in Speech
470(1)
10.4 Multitask Learning
471(11)
10.4.1 Techniques
471(9)
10.4.2 Theory
480(1)
10.4.3 Applications in NLP
480(2)
10.4.4 Applications in Speech Recognition
482(1)
10.5 Case Study
482(7)
10.5.1 Software Tools and Libraries
482(1)
10.5.2 Exploratory Data Analysis
483(1)
10.5.3 Multitask Learning Experiments and Analysis
484(5)
10.5.4 Exercises for Readers and Practitioners
489(1)
References
489(6)
11 Transfer Learning: Domain Adaptation
495(42)
11.1 Introduction
495(22)
11.1.1 Techniques
496(17)
11.1.2 Theory
513(2)
11.1.3 Applications in NLP
515(1)
11.1.4 Applications in Speech Recognition
516(1)
11.2 Zero-Shot, One-Shot, and Few-Shot Learning
517(6)
11.2.1 Zero-Shot Learning
517(3)
11.2.2 One-Shot Learning
520(1)
11.2.3 Few-Shot Learning
521(1)
11.2.4 Theory
522(1)
11.2.5 Applications in NLP and Speech Recognition
522(1)
11.3 Case Study
523(8)
11.3.1 Software Tools and Libraries
524(1)
11.3.2 Exploratory Data Analysis
524(1)
11.3.3 Domain Adaptation Experiments
525(5)
11.3.4 Exercises for Readers and Practitioners
530(1)
References
531(6)
12 End-to-End Speech Recognition
537(38)
12.1 Introduction
537(1)
12.2 Connectionist Temporal Classification (CTC)
538(8)
12.2.1 End-to-End Phoneme Recognition
541(1)
12.2.2 Deep Speech
541(2)
12.2.3 Deep Speech 2
543(1)
12.2.4 Wav2Letter
544(1)
12.2.5 Extensions of CTC
545(1)
12.3 Seq-to-Seq
546(3)
12.3.1 Early Seq-to-Seq ASR
548(1)
12.3.2 Listen, Attend, and Spell (LAS)
548(1)
12.4 Multitask Learning
549(2)
12.5 End-to-End Decoding
551(8)
12.5.1 Language Models for ASR
551(1)
12.5.2 CTC Decoding
552(3)
12.5.3 Attention Decoding
555(1)
12.5.4 Combined Language Model Training
556(1)
12.5.5 Combined CTC-Attention Decoding
557(1)
12.5.6 One-Pass Decoding
558(1)
12.6 Speech Embeddings and Unsupervised Speech Recognition
559(2)
12.6.1 Speech Embeddings
559(1)
12.6.2 Unspeech
560(1)
12.6.3 Audio Word2Vec
560(1)
12.7 Case Study
561(10)
12.7.1 Software Tools and Libraries
561(1)
12.7.2 Deep Speech 2
562(2)
12.7.3 Language Model Training
564(2)
12.7.4 ESPnet
566(4)
12.7.5 Results
570(1)
12.7.6 Exercises for Readers and Practitioners
571(1)
References
571(4)
13 Deep Reinforcement Learning for Text and Speech
575(40)
13.1 Introduction
575(1)
13.2 RL Fundamentals
575(15)
13.2.1 Markov Decision Processes
576(1)
13.2.2 Value, Q, and Advantage Functions
577(1)
13.2.3 Bellman Equations
578(1)
13.2.4 Optimality
579(1)
13.2.5 Dynamic Programming Methods
580(2)
13.2.6 Monte Carlo
582(1)
13.2.7 Temporal Difference Learning
583(3)
13.2.8 Policy Gradient
586(1)
13.2.9 Q-Learning
587(1)
13.2.10 Actor-Critic
588(2)
13.3 Deep Reinforcement Learning Algorithms
590(7)
13.3.1 Why RL for Seq2seq
590(1)
13.3.2 Deep Policy Gradient
591(1)
13.3.3 Deep Q-Learning
592(4)
13.3.4 Deep Advantage Actor-Critic
596(1)
13.4 DRL for Text
597(8)
13.4.1 Information Extraction
597(4)
13.4.2 Text Classification
601(1)
13.4.3 Dialogue Systems
602(1)
13.4.4 Text Summarization
603(2)
13.4.5 Machine Translation
605(1)
13.5 DRL for Speech
605(2)
13.5.1 Automatic Speech Recognition
606(1)
13.5.2 Speech Enhancement and Noise Suppression
606(1)
13.6 Case Study
607(5)
13.6.1 Software Tools and Libraries
607(1)
13.6.2 Text Summarization
608(1)
13.6.3 Exploratory Data Analysis
608(4)
13.6.4 Exercises for Readers and Practitioners
612(1)
References
612(3)
Future Outlook
615(4)
End-to-End Architecture Prevalence
615(1)
Transition to Al-Centric
615(1)
Specialized Hardware
616(1)
Transition Away from Supervised Learning
616(1)
Explainable AI
616(1)
Model Development and Deployment Process
617(1)
Democratization of AI
617(1)
NLP Trends
617(1)
Speech Trends
618(1)
Closing Remarks
618(1)
Index 619
Uday Kamath has more than 20 years of experience architecting and building analytics-based commercial solutions. He currently works as the Chief Analytics Officer at Digital Reasoning, one of the leading companies in AI for NLP and Speech Recognition, heading the Applied Machine Learning research group. Most recently, Uday served as the Chief Data Scientist at BAE Systems Applied Intelligence, building machine learning products and solutions for the financial industry, focused on fraud, compliance, and cybersecurity. Uday has previously authored many books on machine learning such as Machine Learning: End-to-End guide for Java developers: Data Analysis, Machine Learning, and Neural Networks simplified and Mastering Java Machine Learning: A Java developer's guide to implementing machine learning and big data architectures. Uday has published many academic papers in different machine learning journals and conferences. Uday has a Ph.D. in Big Data Machine Learning and was one of the first in generalized scaling of machine learning algorithms using evolutionary computing.





John Liu spent the past 22 years managing quantitative research, portfolio management and data science teams. He is currently CEO of Intelluron Corporation, an emerging AI-as-a-service solution company. Most recently, John was head of data science and data strategy as VP at Digital Reasoning. Previously, he was CIO of Spartus Capital, a quantitative investment firm in New York. Prior to that, John held senior executive roles at Citigroup, where he oversaw the portfolio solutions group that advised institutional clients on quantitative investment and risk strategies; at the Indiana Public Employees pension, where he managed the $7B public equities portfolio; at Vanderbilt University, where he oversaw the $2B equity and alternative investment portfolios; and at BNP Paribas, where he managedthe US index options and MSCI delta-one trading desks. He is known for his expertise in reinforcement learning applied to investment management and has authored numerous papers and book chapters on topics including natural language processing, representation learning, systemic risk, asset allocation, and EM theory. In 2016, John was named Nashville's Data Scientist of the Year. He earned his B.S., M.S., and Ph.D. in electrical engineering from the University of Pennsylvania and is a CFA Charterholder.





James (Jimmy) Whitaker manages Applied Research at Digital Reasoning. He currently leads deep learning developments in speech analytics in the FinTech space, and has spent the last 4 years building machine learning applications for NLP, Speech Recognition, and Computer Vision. He received his masters in Computer Science from the University of Oxford, where he received a distinction for his application of machine learning in the field of Steganalysis after completing his undergraduate degrees in Electrical Engineering and Computer Science from Christian Brothers University. Prior to his work in deep learning, Jimmy worked as a concept engineer and risk manager for complex transportation initiatives.